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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is forthcoming or arriving

    oai_token-act-pair · gpt-3.5-turbo

    the recurring theme of future events or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthodox
    -0.79
    İĭ
    -0.77
    uliffe
    -0.76
    uzzle
    -0.76
    bia
    -0.76
    oller
    -0.75
    ²¾
    -0.75
    hedon
    -0.74
    ording
    -0.73
    dden
    -0.73
    POSITIVE LOGITS
     undone
    1.15
     attractions
    0.90
     forth
    0.84
     forward
    0.82
     together
    0.80
     up
    0.80
    Soon
    0.77
     ashore
    0.77
     apart
    0.77
     out
    0.76
    Act Density 0.031%

    No Known Activations