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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules, requirements, and restrictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.89
    kinson
    -0.78
    eg
    -0.74
    ß
    -0.68
    ortment
    -0.67
    hai
    -0.65
    itton
    -0.61
    ivities
    -0.61
    aples
    -0.60
    kins
    -0.59
    POSITIVE LOGITS
     whatsoever
    1.50
     nor
    1.16
    nor
    0.98
     anymore
    0.94
     slightest
    0.92
     except
    0.83
    except
    0.80
     anybody
    0.77
     anywhere
    0.75
     EVER
    0.72
    Act Density 0.316%

    No Known Activations