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

    Neuronpedia

    INDEX
    Explanations

    contractions that indicate future actions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lda
    -0.75
    ById
    -0.73
    aughtered
    -0.68
    20439
    -0.68
    markets
    -0.67
    fired
    -0.66
     VIDEOS
    -0.66
    Menu
    -0.66
    lehem
    -0.66
    culosis
    -0.65
    POSITIVE LOGITS
     defin
    0.75
     freak
    0.65
     conclud
    0.65
     bang
    0.65
     administ
    0.64
     reconsider
    0.61
     jugg
    0.61
     endeavor
    0.60
     suff
    0.59
     greatly
    0.59
    Act Density 0.037%

    No Known Activations