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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to performance, impact, and social evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <h2>
    -0.72
    ClientSize
    -0.66
    boys
    -0.66
    pezi
    -0.66
    <h1>
    -0.65
     boys
    -0.65
    idential
    -0.64
    ?
    -0.63
    Clik
    -0.61
    girls
    -0.61
    POSITIVE LOGITS
    virons
    0.91
     hinweg
    0.83
     '@/
    0.79
     thereof
    0.78
    ()]
    0.77
    互联网档案馆
    0.77
     voran
    0.76
     obstante
    0.74
     Gump
    0.74
     esferas
    0.73
    Act Density 2.335%

    No Known Activations