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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments related to experiences and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hões
    -0.15
    /tos
    -0.15
    гал
    -0.15
    /umd
    -0.15
    rais
    -0.15
    erap
    -0.14
    วà¸Ķ
    -0.14
    wal
    -0.14
     erotische
    -0.13
    hra
    -0.13
    POSITIVE LOGITS
     Fancy
    0.19
    仲
    0.17
     necessarily
    0.17
     particularly
    0.16
     particular
    0.16
     fancy
    0.15
     STRICT
    0.15
    Segue
    0.15
    OLS
    0.14
    particularly
    0.14
    Act Density 0.128%

    No Known Activations