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

    Neuronpedia

    INDEX
    Explanations

    phrases related to punishment or condemnation

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with punitive actions or legal consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overlap
    -0.74
    ggles
    -0.71
     tilt
    -0.67
     glimps
    -0.67
     resid
    -0.66
     branching
    -0.66
     preview
    -0.64
    ynchron
    -0.64
     narrowing
    -0.63
     Rhythm
    -0.63
    POSITIVE LOGITS
     ASAP
    1.36
     lest
    0.98
     whoever
    0.89
     wherever
    0.87
     sooner
    0.84
     preferably
    0.83
     someday
    0.81
     unless
    0.81
     punishable
    0.81
     perpetrators
    0.80
    Act Density 0.570%

    No Known Activations