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

    Neuronpedia

    INDEX
    Explanations

    instances of language or terminology

    oai_token-act-pair · gpt-3.5-turbo

    references to language used in legal or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.77
    iary
    -0.74
    cot
    -0.74
    rients
    -0.68
    iaries
    -0.66
    TAIN
    -0.66
    opia
    -0.65
     Maurit
    -0.63
    umeric
    -0.63
    rique
    -0.63
    POSITIVE LOGITS
    mith
    0.87
     barriers
    0.83
    witz
    0.82
    anguage
    0.79
     spoken
    0.78
     eloqu
    0.75
     describing
    0.72
     surrounding
    0.71
     constructs
    0.71
     language
    0.71
    Act Density 0.080%

    No Known Activations