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

    Neuronpedia

    INDEX
    Explanations

    phrases where the concept of 'being fine' or 'acceptable' is expressed

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approval or adequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riber
    -0.77
    rush
    -0.73
    orical
    -0.71
     Kut
    -0.70
    iq
    -0.70
    Hack
    -0.70
    nikov
    -0.69
    raped
    -0.69
    ulhu
    -0.69
    erity
    -0.67
    POSITIVE LOGITS
     tuning
    1.02
     tuned
    0.94
     Gael
    0.83
     tune
    0.78
     fine
    0.74
    Fine
    0.74
     Haven
    0.71
    fine
    0.71
     Fine
    0.70
    baum
    0.70
    Act Density 0.010%

    No Known Activations