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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing disbelief in the existence of something

    oai_token-act-pair · gpt-3.5-turbo

    statements that emphasize the non-existence of various concepts or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Þ
    -0.80
    ÃĥÃĤ
    -0.79
    ß
    -0.79
    ÃĥÃĤÃĥÃĤ
    -0.73
    ô
    -0.72
    alf
    -0.70
    qt
    -0.68
    Ý
    -0.68
    yip
    -0.67
     practition
    -0.67
    POSITIVE LOGITS
     escaping
    0.75
    ointed
    0.72
     recourse
    0.70
     anybody
    0.69
     difference
    0.68
    ifiable
    0.68
     shortage
    0.68
     antidote
    0.68
     escape
    0.68
    atable
    0.66
    Act Density 0.167%

    No Known Activations