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

    Neuronpedia

    INDEX
    Explanations

    references to smoking activities and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adele
    -0.15
    errat
    -0.14
    otts
    -0.14
    uppy
    -0.13
     hostages
    -0.13
     بع
    -0.13
     hostage
    -0.13
    ç§ĭ
    -0.12
    CTL
    -0.12
    brightness
    -0.12
    POSITIVE LOGITS
     cigarettes
    0.35
     tobacco
    0.33
     cigarette
    0.33
     pipe
    0.32
     pipes
    0.31
     cigars
    0.30
     smoking
    0.29
     cigar
    0.28
     Pipes
    0.27
     smoke
    0.27
    Act Density 0.045%

    No Known Activations