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

    Neuronpedia

    INDEX
    Explanations

    verbs related to forceful actions, particularly those which involve criticism or punishment

    oai_token-act-pair · gpt-3.5-turbo

    verbs and terms related to impact or forceful actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lio
    -0.85
    enhagen
    -0.82
    alian
    -0.80
    yne
    -0.77
    lement
    -0.76
    resso
    -0.74
    lia
    -0.71
    erv
    -0.71
    fly
    -0.70
    lements
    -0.70
    POSITIVE LOGITS
    ization
    0.80
    âĺħâĺħ
    0.78
     dunk
    0.74
    ocker
    0.74
    ized
    0.73
     Jenner
    0.68
    boarding
    0.67
    icago
    0.65
     knit
    0.65
     Dunk
    0.63
    Act Density 0.113%

    No Known Activations