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

    Neuronpedia

    INDEX
    Explanations

    negative qualifiers related to actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONTAL
    -0.16
    etti
    -0.15
    ova
    -0.15
    krom
    -0.15
    ois
    -0.15
    es
    -0.14
    ansk
    -0.14
    lobby
    -0.14
    onas
    -0.14
    Ñģен
    -0.14
    POSITIVE LOGITS
    isnan
    0.18
     necessarily
    0.16
    itlement
    0.15
    riger
    0.15
    aken
    0.14
    door
    0.14
     Doch
    0.14
    ori
    0.14
    qui
    0.13
    Äĩe
    0.13
    Act Density 0.032%

    No Known Activations