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

    Neuronpedia

    INDEX
    Explanations

    words related to negativity or negation

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases associated with negativity or negative concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bloom
    -0.80
    realDonaldTrump
    -0.74
    SPONSORED
    -0.72
    BuyableInstoreAndOnline
    -0.69
    OPLE
    -0.66
     Falk
    -0.65
     Mour
    -0.64
    åŃIJ
    -0.63
     Takeru
    -0.62
    Fly
    -0.62
    POSITIVE LOGITS
    oti
    1.61
    otiation
    1.58
    atives
    1.31
    ativity
    1.26
    lected
    1.12
    lect
    1.11
    atively
    1.09
    neg
    1.09
    rito
    1.08
    oci
    1.04
    Act Density 0.030%

    No Known Activations