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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative experiences or situations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and specific adverbial or prepositional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scaven
    -0.59
     Murray
    -0.56
     difference
    -0.56
     pi
    -0.56
    of
    -0.55
     flo
    -0.55
     fish
    -0.52
     Flores
    -0.52
     scient
    -0.51
    iom
    -0.51
    POSITIVE LOGITS
    soDeliveryDate
    1.24
    SourceFile
    0.94
    rawdownloadcloneembedreportprint
    0.94
    ÃįÃį
    0.94
    âĹ¼
    0.92
    ombat
    0.88
    pload
    0.83
    20439
    0.82
    è£ħ
    0.80
     guiActiveUn
    0.75
    Act Density 0.839%

    No Known Activations