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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating communication and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.04
    4:0.07
    5:0.03
    6:0.35
    7:0.11
    8:0.04
    9:0.04
    10:0.09
    11:0.05
    Negative Logits
    ��
    -1.27
    axis
    -1.19
    iability
    -1.17
    bilt
    -1.15
     suited
    -1.12
     pens
    -1.08
     manageable
    -1.06
    ingers
    -1.03
     amusement
    -1.02
     Obj
    -1.02
    POSITIVE LOGITS
    ordinate
    1.30
    alore
    1.29
    adr
    1.27
    illin
    1.25
    mail
    1.24
    pur
    1.22
    PsyNetMessage
    1.21
    ai
    1.20
    rahim
    1.19
     reinforcements
    1.19
    Act Density 0.008%

    No Known Activations