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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing detailed explanations or inquiries about specific subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.10
    3:0.04
    4:0.30
    5:0.06
    6:0.02
    7:0.02
    8:0.06
    9:0.22
    10:0.05
    11:0.02
    Negative Logits
     gasp
    -1.44
    assador
    -1.34
    ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ
    -1.33
    interstitial
    -1.28
     Adin
    -1.28
    anova
    -1.23
    rals
    -1.22
    ush
    -1.21
     Sidney
    -1.21
    inia
    -1.20
    POSITIVE LOGITS
    ��
    1.82
     Transcript
    1.34
     unfolding
    1.30
     detail
    1.29
     detailing
    1.29
    erous
    1.28
    ascript
    1.27
    ��
    1.26
     Firearms
    1.26
    hyde
    1.26
    Act Density 0.017%

    No Known Activations