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

    Neuronpedia

    INDEX
    Explanations

    numbers within text related to factual data or statistics

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

    phrases indicating location or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.12
    3:0.25
    4:0.16
    5:0.13
    6:0.02
    7:0.01
    8:0.05
    9:0.08
    10:0.04
    11:0.02
    Negative Logits
     Sakuya
    -1.21
    onite
    -1.11
     ATI
    -1.11
    leasing
    -1.07
    ply
    -1.07
     1050
    -1.05
    vier
    -1.04
     endif
    -1.02
     deterrent
    -1.01
     ●
    -1.01
    POSITIVE LOGITS
    �
    1.26
    Interstitial
    1.17
    iggurat
    1.17
    igi
    1.15
     happiest
    1.14
     immunity
    1.13
     theat
    1.12
    Ja
    1.12
     Spartans
    1.12
    perty
    1.10
    Act Density 0.060%

    No Known Activations