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

    Neuronpedia

    INDEX
    Explanations

    nouns and proper names associated with noteworthy individuals or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fully
    -0.17
    elijke
    -0.17
    elian
    -0.17
    fulness
    -0.17
    lessly
    -0.16
    ãģĦãģ¦
    -0.16
    holes
    -0.15
    ëĿ½
    -0.15
    hole
    -0.14
     antlr
    -0.14
    POSITIVE LOGITS
    mente
    0.38
    ities
    0.31
    ity
    0.30
    ness
    0.26
    -minded
    0.24
    most
    0.22
    ized
    0.21
    zeitig
    0.20
    zza
    0.20
    idad
    0.20
    Act Density 0.821%

    No Known Activations