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

    Neuronpedia

    INDEX
    Explanations

    code snippets or technical terms related to computing and programming

    oai_token-act-pair · gpt-3.5-turbo

    colons and their associated values that likely represent data structure elements or attributes in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behavi
    -0.86
     outright
    -0.71
    Reilly
    -0.68
    ynes
    -0.67
    aston
    -0.66
    hett
    -0.65
     behav
    -0.64
     predicament
    -0.63
    eston
    -0.60
     tremend
    -0.60
    POSITIVE LOGITS
    hover
    0.95
    YES
    0.83
    cv
    0.82
     Logged
    0.81
    latest
    0.81
    mount
    0.78
    pub
    0.73
    checked
    0.73
    344
    0.73
    sic
    0.73
    Act Density 0.107%

    No Known Activations