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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential actions, decisions, or opinions

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or phrases indicating hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.65
     Shots
    -0.62
    Introduced
    -0.60
    senal
    -0.59
    OTA
    -0.58
    IDES
    -0.58
     Passenger
    -0.58
    iling
    -0.56
    HT
    -0.56
    View
    -0.56
    POSITIVE LOGITS
     raining
    0.95
     beh
    0.88
    etsk
    0.78
     dawn
    0.76
    iner
    0.76
     unclear
    0.73
    ÃĥÃĤ
    0.73
     easier
    0.71
     ironic
    0.70
     impossible
    0.68
    Act Density 0.218%

    No Known Activations