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

    Neuronpedia

    INDEX
    Explanations

    numerical values in a technical context and instructions on setting variables

    oai_token-act-pair · gpt-3.5-turbo

    references to values and value assignments in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ility
    -0.79
    ooks
    -0.73
    dar
    -0.72
    elia
    -0.68
    alyst
    -0.68
    ocamp
    -0.68
    udeb
    -0.68
    icip
    -0.68
    osaurus
    -0.67
    asio
    -0.66
    POSITIVE LOGITS
     value
    0.76
    EStream
    0.76
     values
    0.75
    variable
    0.69
     stored
    0.65
     fluct
    0.65
    values
    0.65
    VALUE
    0.64
    lda
    0.64
     computed
    0.63
    Act Density 0.015%

    No Known Activations