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

    Neuronpedia

    INDEX
    Explanations

    phrases related to probability or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating chances or probabilities of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minus
    -0.91
    heses
    -0.79
    hesis
    -0.79
    Sport
    -0.76
    arse
    -0.74
    idelines
    -0.73
    raq
    -0.73
    ms
    -0.73
    CSS
    -0.72
    entric
    -0.72
    POSITIVE LOGITS
     obtaining
    1.11
     getting
    0.97
     encountering
    0.97
     completing
    0.95
     escaping
    0.95
     acquiring
    0.94
     reaching
    0.94
     resolving
    0.93
     preserving
    0.93
     achieving
    0.92
    Act Density 0.118%

    No Known Activations