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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "When"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "When."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kaya
    -0.84
    whatever
    -0.77
    ouble
    -0.71
    uther
    -0.70
    omore
    -0.67
    \\\\\\\\
    -0.66
    ruption
    -0.66
    bright
    -0.65
    oof
    -0.65
    stead
    -0.64
    POSITIVE LOGITS
     asked
    1.21
     confronted
    1.14
    soever
    1.01
     contacted
    0.98
     pressed
    0.98
     faced
    0.98
     discussing
    0.97
     you
    0.90
     questioned
    0.89
     comparing
    0.87
    Act Density 0.083%

    No Known Activations