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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that indicate existence, presence, or the potential to achieve something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lick
    -0.17
    eger
    -0.16
     Vit
    -0.15
    ulp
    -0.15
    uo
    -0.14
     Phelps
    -0.14
    amed
    -0.14
    iola
    -0.14
    x
    -0.14
     special
    -0.14
    POSITIVE LOGITS
     cigaret
    0.18
    سط
    0.16
    ernals
    0.16
    .Guna
    0.15
     Sutton
    0.15
    vsp
    0.15
    avras
    0.15
    ãģ®ãģĮ
    0.15
    .Bunifu
    0.15
    ÑĢаз
    0.14
    Act Density 0.040%

    No Known Activations