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

    Neuronpedia

    INDEX
    Explanations

    references to letters and communication directed to various officials or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.03
    2:0.06
    3:0.15
    4:0.01
    5:0.03
    6:0.05
    7:0.12
    8:0.06
    9:0.24
    10:0.07
    11:0.10
    Negative Logits
    �
    -1.20
    sic
    -1.20
    ahime
    -1.16
    ォ
    -1.13
    staking
    -1.11
    APTER
    -1.10
    AMI
    -1.09
    roo
    -1.09
    wagen
    -1.09
    デ
    -1.07
    POSITIVE LOGITS
     Gulf
    1.11
    idium
    1.10
    inyl
    1.06
     solicit
    1.04
    ockets
    1.03
     clipboard
    1.02
     envelop
    1.01
    clus
    1.00
     behalf
    0.98
     flyer
    0.98
    Act Density 0.016%

    No Known Activations