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

    Neuronpedia

    INDEX
    Explanations

    the word "when" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss the timing or occurrence of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.76
    gur
    -0.67
    aking
    -0.66
    kaya
    -0.66
    feature
    -0.64
    lator
    -0.64
    hid
    -0.63
    ortment
    -0.63
    orter
    -0.63
    POR
    -0.63
    POSITIVE LOGITS
    soever
    1.13
     exactly
    1.05
    abouts
    0.85
    ce
    0.75
     else
    0.72
     they
    0.64
     puberty
    0.64
    ||||
    0.62
    actly
    0.61
     faced
    0.60
    Act Density 0.077%

    No Known Activations