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

    Neuronpedia

    INDEX
    Explanations

    phrases that reflect a sense of critique or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idot
    -0.16
    etical
    -0.15
    licative
    -0.15
    ازÛĮ
    -0.14
    _SPELL
    -0.14
    enerative
    -0.14
    654
    -0.14
    jom
    -0.14
    wins
    -0.14
    ANCEL
    -0.14
    POSITIVE LOGITS
    ibus
    0.18
    modo
    0.17
    inci
    0.16
    aeper
    0.15
    izzle
    0.15
    etur
    0.15
     Script
    0.14
    ici
    0.14
     aliqu
    0.14
     typeof
    0.13
    Act Density 0.012%

    No Known Activations