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

    Neuronpedia

    INDEX
    Explanations

    words related to disruptive or destructive actions or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to harmful or detrimental actions and influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igon
    -0.84
    buck
    -0.78
    elf
    -0.76
    puter
    -0.76
    olina
    -0.75
    hung
    -0.75
    aintain
    -0.73
    obyl
    -0.72
    obbies
    -0.72
    ille
    -0.71
    POSITIVE LOGITS
     impulses
    0.93
     impulse
    0.91
     measures
    0.89
     tendencies
    0.88
     behav
    0.87
     qualities
    0.82
     behaviour
    0.80
     activity
    0.77
     intent
    0.76
     gestures
    0.74
    Act Density 0.066%

    No Known Activations