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

    Neuronpedia

    INDEX
    Explanations

    concepts related to universal declarations and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iw
    -0.20
    lessly
    -0.17
    aben
    -0.16
    leton
    -0.15
    lessness
    -0.15
    esar
    -0.15
    Ïĥκ
    -0.14
    alo
    -0.14
    yonel
    -0.14
    eo
    -0.14
    POSITIVE LOGITS
    izing
    0.22
    ize
    0.22
    ized
    0.22
    ist
    0.21
    ities
    0.21
    ised
    0.20
    ists
    0.19
    istic
    0.18
    mente
    0.18
    ization
    0.18
    Act Density 0.014%

    No Known Activations