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

    Neuronpedia

    INDEX
    Explanations

    instances of transparency and visual obstructions in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     boucles
    -0.48
    griffe
    -0.43
    ősz
    -0.43
     multi
    -0.42
    griffen
    -0.41
    áv
    -0.41
    onenumber
    -0.40
    ENNA
    -0.40
    Repeating
    -0.40
    χε
    -0.40
    POSITIVE LOGITS
    ftagPool
    0.89
    الحياه
    0.81
    OGND
    0.74
    ModelAdmin
    0.73
     nakalista
    0.71
     Exactos
    0.68
    PasswordEncoder
    0.68
     NSCoder
    0.67
    ilage
    0.66
     visibility
    0.65
    Act Density 0.241%

    No Known Activations