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

    Neuronpedia

    INDEX
    Explanations

    words related to the potential or possibility of a situation occurring

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    biz
    -0.78
    book
    -0.77
    neck
    -0.73
    horn
    -0.70
    chens
    -0.68
    cup
    -0.68
    elle
    -0.66
     Deadline
    -0.65
    minus
    -0.65
    ele
    -0.65
    POSITIVE LOGITS
     leverage
    0.97
     advancement
    0.89
     misuse
    0.85
     reuse
    0.85
     future
    0.83
     breakthrough
    0.83
     enrich
    0.82
     escape
    0.80
     redemption
    0.80
     mischief
    0.79
    Act Density 0.085%

    No Known Activations