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

    Neuronpedia

    INDEX
    Explanations

    instances where there's a likelihood or possibility of an event occurring

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the likelihood or probability of an event occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.88
    zeb
    -0.77
    cht
    -0.75
    ilver
    -0.73
    empl
    -0.72
    Materials
    -0.72
    Keys
    -0.71
    ils
    -0.71
    ashion
    -0.69
    artney
    -0.68
    POSITIVE LOGITS
    llor
    0.81
     Rouhani
    0.79
     probability
    0.76
     pron
    0.71
     occurrence
    0.71
     admission
    0.70
     inacc
    0.69
     chance
    0.69
     likelihood
    0.69
    finder
    0.68
    Act Density 0.055%

    No Known Activations