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

    Neuronpedia

    INDEX
    Explanations

    architectural elements and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acf
    -0.17
    ushima
    -0.16
    ouser
    -0.16
    endir
    -0.16
    ève
    -0.15
    Slug
    -0.15
    946
    -0.15
    acket
    -0.14
    415
    -0.14
    amma
    -0.13
    POSITIVE LOGITS
     fend
    0.22
     trap
    0.20
     bomb
    0.18
    lettes
    0.17
     roses
    0.17
     droits
    0.17
    gross
    0.16
     dispos
    0.16
     rect
    0.16
     couch
    0.16
    Act Density 0.034%

    No Known Activations