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

    Neuronpedia

    INDEX
    Explanations

    terms related to horned mammals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    itton
    -0.68
    senal
    -0.64
    tein
    -0.63
     compr
    -0.62
    iannopoulos
    -0.61
    TI
    -0.60
     Hurt
    -0.58
     depreciation
    -0.58
    urious
    -0.57
    kefeller
    -0.56
    POSITIVE LOGITS
    erella
    1.30
    icator
    1.12
    icative
    1.08
    irect
    1.07
    ebted
    1.05
    ications
    1.00
    icators
    0.99
    ividually
    0.98
    sight
    0.96
    rift
    0.92
    Act Density 0.015%

    No Known Activations