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

    Neuronpedia

    INDEX
    Explanations

    information regarding numerical thresholds or requirements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that specify a minimum quantity or requirement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.73
    tions
    -0.69
    quit
    -0.64
    bath
    -0.64
    axter
    -0.62
     Dynamics
    -0.61
    ãĤ¿
    -0.60
    Generic
    -0.59
    rats
    -0.59
    HCR
    -0.58
    POSITIVE LOGITS
     partially
    0.84
    uner
    0.79
     partly
    0.74
     toler
    0.73
    lik
    0.68
    omething
    0.67
     SOME
    0.66
     intellectually
    0.65
     superf
    0.63
     theoretically
    0.62
    Act Density 0.025%

    No Known Activations