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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey comparisons or similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¾ãģŁ
    -0.17
    usercontent
    -0.15
     ëijĺ
    -0.13
    ange
    -0.13
    _then
    -0.13
    ERSHEY
    -0.13
    tır
    -0.13
    igo
    -0.13
    orno
    -0.13
    ycopg
    -0.13
    POSITIVE LOGITS
     ones
    0.34
    ones
    0.30
     those
    0.30
     ours
    0.24
    those
    0.22
     Ones
    0.22
    :
    0.21
     напÑĢимеÑĢ
    0.21
     napÅĻ
    0.20
     yours
    0.19
    Act Density 0.152%

    No Known Activations