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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    instances or conditions related to "when" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rolet
    -0.82
    angler
    -0.76
    oslov
    -0.74
    kaya
    -0.71
    iosyncr
    -0.71
    elman
    -0.70
    yright
    -0.70
    english
    -0.69
    ilton
    -0.65
    ibble
    -0.65
    POSITIVE LOGITS
     confronted
    1.21
     faced
    1.12
    soever
    1.03
     someone
    0.95
     somebody
    0.93
     encountering
    0.88
     suddenly
    0.86
     they
    0.86
     things
    0.85
     others
    0.85
    Act Density 0.112%

    No Known Activations