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

    Neuronpedia

    INDEX
    Explanations

    references to female pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.02
    2:0.27
    3:0.06
    4:0.07
    5:0.04
    6:0.07
    7:0.08
    8:0.04
    9:0.03
    10:0.07
    11:0.09
    Negative Logits
     confidentiality
    -1.82
     urgency
    -1.74
     ZIP
    -1.72
     estrogen
    -1.63
     guiActiveUnfocused
    -1.56
     Buckingham
    -1.54
     respectively
    -1.53
     inoc
    -1.50
     Appalach
    -1.50
     contraceptives
    -1.49
    POSITIVE LOGITS
    usky
    2.18
     Archdemon
    2.10
    BUG
    1.92
    antom
    1.90
    /​
    1.89
    ��
    1.84
    urch
    1.84
    utt
    1.82
    zek
    1.78
    kinson
    1.76
    Act Density 0.000%

    No Known Activations