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

    Neuronpedia

    INDEX
    Explanations

    words related to strangeness, peculiarity, or unconventional aspects

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the concept of "weirdness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vation
    -0.88
    ptive
    -0.86
    ptives
    -0.84
    adr
    -0.83
    cussion
    -0.83
    thood
    -0.81
    aders
    -0.79
    Interstitial
    -0.78
    ailable
    -0.76
    apers
    -0.76
    POSITIVE LOGITS
    ness
    1.06
    ly
    0.96
    nesses
    0.88
    ishly
    0.83
    est
    0.82
    entimes
    0.81
    ety
    0.79
     Weird
    0.77
     weird
    0.76
    oes
    0.75
    Act Density 0.009%

    No Known Activations