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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating specific relationships

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating relationships or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãħĭãħĭ
    -0.65
    bara
    -0.65
    iga
    -0.59
    alore
    -0.59
    berman
    -0.58
    âĿ
    -0.58
    doesn
    -0.58
    lance
    -0.58
     therein
    -0.58
     :=
    -0.58
    POSITIVE LOGITS
     unrelated
    0.66
    CLASSIFIED
    0.66
    ãĥĨãĤ£
    0.64
    cial
    0.63
    vol
    0.62
    20439
    0.59
    pless
    0.58
     inst
    0.57
    Ô
    0.57
    cific
    0.56
    Act Density 0.263%

    No Known Activations