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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tyr
    -0.88
    oshenko
    -0.82
     footing
    -0.77
     suspic
    -0.75
     purse
    -0.73
     metic
    -0.73
     volunte
    -0.72
     enthusi
    -0.72
     boarded
    -0.71
     gunfire
    -0.71
    POSITIVE LOGITS
     However
    1.21
     Therefore
    1.16
     Additionally
    1.15
     Unfortunately
    1.14
     Depending
    1.12
     Alternatively
    1.11
     Typically
    1.08
     Ideally
    1.07
     Whilst
    1.07
     Personally
    1.05
    Act Density 1.504%

    No Known Activations