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

    Neuronpedia

    INDEX
    Explanations

    words related to strange or unusual situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bizarre" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rien
    -0.80
    claimer
    -0.78
    abet
    -0.73
    onder
    -0.73
    league
    -0.73
    yer
    -0.72
    mop
    -0.71
    ophers
    -0.70
    aper
    -0.69
    adr
    -0.69
    POSITIVE LOGITS
    ly
    1.33
    ishly
    0.94
     antics
    0.89
     bizarre
    0.86
    ulously
    0.83
     twists
    0.82
    ively
    0.77
    ingly
    0.75
     hallucinations
    0.74
     occurrences
    0.73
    Act Density 0.021%

    No Known Activations