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

    Neuronpedia

    INDEX
    Explanations

    references to friendships or close relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.10
    3:0.08
    4:0.06
    5:0.07
    6:0.08
    7:0.09
    8:0.08
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
    Fourth
    -2.87
    Ire
    -2.71
    ··
    -2.63
     Relief
    -2.56
    ento
    -2.50
    collect
    -2.49
    mary
    -2.48
    xtap
    -2.47
    iliar
    -2.46
    Marginal
    -2.45
    POSITIVE LOGITS
     Chao
    2.99
    �
    2.97
     Zeus
    2.85
     ASUS
    2.77
     Nur
    2.74
     Dmitry
    2.71
     Indones
    2.70
     jung
    2.67
     Emin
    2.62
     Krishna
    2.59
    Act Density 0.000%

    No Known Activations