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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating compatibility or fitting well together

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to compatibility and effectiveness in relationships or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ittance
    -0.72
    ithing
    -0.69
    arthed
    -0.63
    ewitness
    -0.63
    uploads
    -0.62
    oldown
    -0.62
    rez
    -0.60
    Winged
    -0.58
    tein
    -0.58
    ibi
    -0.58
    POSITIVE LOGITS
     nicely
    1.77
     better
    1.68
     poorly
    1.67
     perfectly
    1.65
     well
    1.65
     beautifully
    1.61
     brilliantly
    1.49
     wonderfully
    1.48
     best
    1.41
     differently
    1.40
    Act Density 0.711%

    No Known Activations