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

    Neuronpedia

    INDEX
    Explanations

    words related to uncertainty or unpredictability

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words related to uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.91
    endar
    -0.82
    ILA
    -0.80
    clerosis
    -0.79
    ovie
    -0.78
    ingo
    -0.78
    agos
    -0.78
    gdala
    -0.77
    emetery
    -0.76
    berman
    -0.76
    POSITIVE LOGITS
    ly
    0.92
     shorth
    0.85
    lessly
    0.77
    ingly
    0.76
    ively
    0.75
    ially
    0.73
     doom
    0.72
    lly
    0.70
    erness
    0.69
     uncertain
    0.68
    Act Density 0.009%

    No Known Activations