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

    Neuronpedia

    INDEX
    Explanations

    names and terms associated with individuals, likely in the context of cultural or entertainment references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auen
    -0.19
    ariat
    -0.18
    oppel
    -0.17
    edir
    -0.15
    tere
    -0.15
    oint
    -0.15
    lue
    -0.15
    cona
    -0.14
    odem
    -0.14
    .bunifuFlatButton
    -0.14
    POSITIVE LOGITS
    aceutical
    0.20
    esse
    0.16
    esian
    0.16
    elize
    0.16
    fully
    0.16
    acist
    0.16
    ichael
    0.16
    stadt
    0.15
    aged
    0.15
    ington
    0.15
    Act Density 0.035%

    No Known Activations