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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    oai_token-act-pair · gpt-3.5-turbo

    parentheses or other grouping symbols in relationships and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     peanut
    -0.70
     Scientology
    -0.66
     hypers
    -0.66
     petroleum
    -0.65
     minded
    -0.63
     Renew
    -0.62
     Bever
    -0.62
     bricks
    -0.62
     journalism
    -0.62
     hops
    -0.61
    POSITIVE LOGITS
    emphasis
    1.11
    ...)
    1.09
    âĢ¦)
    1.09
    ++)
    1.01
    aka
    0.98
    edited
    0.96
    laughs
    0.93
    *)
    0.93
    ?)
    0.91
    ii
    0.88
    Act Density 0.086%

    No Known Activations