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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing satisfaction or approval regarding quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lsa
    -0.15
    ahoo
    -0.15
    ativo
    -0.15
    adoo
    -0.15
    ää
    -0.15
    akte
    -0.15
    wed
    -0.14
    uffers
    -0.14
    scri
    -0.14
    asta
    -0.14
    POSITIVE LOGITS
     Pam
    0.15
    711
    0.14
    _tE
    0.14
    661
    0.14
     vál
    0.14
    Ñĥж
    0.14
    ">//
    0.14
     Slut
    0.13
    urgeon
    0.13
     Minority
    0.13
    Act Density 0.348%

    No Known Activations