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

    Neuronpedia

    INDEX
    Explanations

    statements indicating the presence or absence of certain conditions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.84
     those
    -0.83
     paar
    -0.73
     many
    -0.73
     are
    -0.72
    many
    -0.71
    wsze
    -0.70
     few
    -0.69
     yourselves
    -0.69
     mga
    -0.67
    POSITIVE LOGITS
     neuem
    0.96
    __*/
    0.95
     weißem
    0.87
    ChildScrollView
    0.84
    Filmographie
    0.82
    ciety
    0.81
    principalColumn
    0.80
     pouvoirs
    0.80
     purpoſe
    0.80
     iſt
    0.79
    Act Density 0.434%

    No Known Activations