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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ongoing actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atana
    -0.73
    idden
    -0.73
    aster
    -0.72
    ranch
    -0.71
    oster
    -0.70
    ixed
    -0.70
    worker
    -0.70
    ramid
    -0.69
    ool
    -0.68
    onomic
    -0.67
    POSITIVE LOGITS
     unab
    0.86
     ap
    0.73
     unanswered
    0.71
     uninterrupted
    0.70
     adolesc
    0.69
     unchanged
    0.69
     momentum
    0.67
     unravel
    0.64
     trending
    0.64
     tremend
    0.64
    Act Density 0.035%

    No Known Activations