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

    Neuronpedia

    INDEX
    Explanations

    mentions of places or food ingredients in a text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurements, quantities, or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adder
    -0.69
    aundering
    -0.66
    clinton
    -0.66
     judgment
    -0.66
    adders
    -0.64
    kinson
    -0.63
    gewater
    -0.61
    izont
    -0.61
    isha
    -0.61
    paren
    -0.60
    POSITIVE LOGITS
    vous
    0.79
     Vide
    0.76
    urious
    0.76
    opus
    0.75
    uits
    0.74
    umbnail
    0.73
    avier
    0.72
    ery
    0.72
    xon
    0.71
    enced
    0.69
    Act Density 0.028%

    No Known Activations