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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions or changes

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions related to physical processes and changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ican
    -0.79
    ourt
    -0.74
    responsible
    -0.63
    ifestyle
    -0.63
    ãĥª
    -0.62
    onnaissance
    -0.61
    ft
    -0.60
     deleg
    -0.60
    ivan
    -0.60
     tackling
    -0.59
    POSITIVE LOGITS
     smoothly
    1.07
     spontaneously
    1.02
     unpredict
    0.89
     uncontroll
    0.89
     into
    0.84
     explos
    0.84
     underneath
    0.83
     beneath
    0.83
     naturally
    0.83
     evenly
    0.82
    Act Density 0.321%

    No Known Activations