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

    Neuronpedia

    INDEX
    Explanations

    words related to the duration and operation of events or services

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "run" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.72
    axter
    -0.70
    omical
    -0.69
    iasco
    -0.65
    htaking
    -0.64
    orical
    -0.64
    alam
    -0.64
    ippy
    -0.62
    actory
    -0.61
    Birth
    -0.61
    POSITIVE LOGITS
    running
    0.92
    gs
    0.92
     rampant
    0.83
    swick
    0.82
    escape
    0.81
    around
    0.81
    ners
    0.79
     af
    0.77
    aways
    0.77
    lasses
    0.76
    Act Density 0.045%

    No Known Activations