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

    Neuronpedia

    INDEX
    Explanations

    terms related to various forms of existence and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozor
    -0.17
    ór
    -0.17
    kara
    -0.15
    ramento
    -0.14
    eb
    -0.14
     stÅĻednÃŃ
    -0.14
    HEME
    -0.14
    tur
    -0.14
    ewe
    -0.13
    oving
    -0.13
    POSITIVE LOGITS
    ism
    0.27
    ity
    0.25
    ities
    0.22
    idad
    0.21
    isme
    0.19
    ISM
    0.19
    ITY
    0.18
    iteit
    0.17
    idade
    0.16
    izm
    0.15
    Act Density 0.160%

    No Known Activations