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

    Neuronpedia

    INDEX
    Explanations

    Italian words related to various professional domains

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "un" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INGS
    -0.64
    Previously
    -0.64
    OSH
    -0.63
     wisely
    -0.62
    olls
    -0.58
    Jews
    -0.57
    wolves
    -0.57
    RD
    -0.57
     aloud
    -0.57
    orney
    -0.56
    POSITIVE LOGITS
    idad
    0.82
    itud
    0.76
    iver
    0.75
     mund
    0.75
    ctor
    0.72
    ifier
    0.72
     gran
    0.70
    ici
    0.69
    na
    0.69
    assisted
    0.68
    Act Density 0.010%

    No Known Activations