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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a requirement for performing specific actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Discuss
    -0.64
    TG
    -0.62
    weed
    -0.60
     merger
    -0.59
    iddle
    -0.57
     Thank
    -0.56
    undown
    -0.55
    ilings
    -0.55
    icy
    -0.54
    patch
    -0.54
    POSITIVE LOGITS
     been
    1.08
     recourse
    1.02
     gotta
    0.96
    been
    0.94
     choices
    0.87
     begun
    0.86
     gotten
    0.84
     gone
    0.82
     options
    0.81
     chosen
    0.81
    Act Density 0.216%

    No Known Activations