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

    Neuronpedia

    INDEX
    Explanations

    words related to locations or points in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "where"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     independently
    -0.61
     tolerated
    -0.60
    nature
    -0.59
     dumped
    -0.57
    cat
    -0.57
     uncond
    -0.56
    Friday
    -0.56
    straight
    -0.56
    spell
    -0.56
    Jenn
    -0.56
    POSITIVE LOGITS
     things
    0.76
     tragedies
    0.71
    illon
    0.66
    ushima
    0.65
    ij士
    0.65
     specialization
    0.64
    upon
    0.64
    vantage
    0.63
    buquerque
    0.63
    modules
    0.62
    Act Density 0.067%

    No Known Activations