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

    Neuronpedia

    INDEX
    Explanations

    content related to investigations and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rover
    -0.15
    ehir
    -0.14
    chnitt
    -0.14
    acker
    -0.14
    atrix
    -0.14
    landing
    -0.14
    alias
    -0.13
    üny
    -0.13
    çĮľ
    -0.13
     prompt
    -0.13
    POSITIVE LOGITS
    ани
    0.16
    baugh
    0.15
    rought
    0.15
    idot
    0.15
    âķĿ
    0.15
     Midi
    0.14
    pose
    0.14
     med
    0.14
    plet
    0.14
    subcategory
    0.14
    Act Density 0.324%

    No Known Activations