Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal terms, rights, and security

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to pleasure and enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.03
    2:0.19
    3:0.05
    4:0.22
    5:0.06
    6:0.03
    7:0.03
    8:0.06
    9:0.14
    10:0.05
    11:0.03
    Negative Logits
    Maps
    -1.44
    �
    -1.42
    alde
    -1.32
    IR
    -1.25
    �
    -1.21
    �
    -1.18
    rahim
    -1.17
    edin
    -1.17
    nis
    -1.16
    Cod
    -1.16
    POSITIVE LOGITS
     restraint
    1.28
     distraction
    1.26
     pleas
    1.22
     persuasion
    1.22
     consistency
    1.22
     feminine
    1.20
     calming
    1.18
     representations
    1.16
     behaviour
    1.15
     tactile
    1.13
    Act Density 0.001%

    No Known Activations