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

    Neuronpedia

    INDEX
    Explanations

    words related to physical proximity or scrutiny

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to close observation and scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bir
    -0.68
     Ame
    -0.65
    ij士
    -0.63
     Pog
    -0.62
     Palest
    -0.61
     delinqu
    -0.61
     Brav
    -0.61
     Lerner
    -0.60
     Nile
    -0.59
     Herrera
    -0.59
    POSITIVE LOGITS
    nery
    0.81
    ptives
    0.80
    alore
    0.77
    nered
    0.73
    aminer
    0.72
    atches
    0.71
    essional
    0.70
    apixel
    0.69
    piring
    0.69
    enment
    0.69
    Act Density 0.093%

    No Known Activations