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

    Neuronpedia

    INDEX
    Explanations

    instances of persuasive language and power dynamics in interpersonal or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     î¡
    -0.17
    unami
    -0.15
    evi
    -0.15
    odesk
    -0.15
    _,,
    -0.15
    ropp
    -0.15
    niž
    -0.15
     seins
    -0.15
    ÂłÙħ
    -0.14
    iginal
    -0.14
    POSITIVE LOGITS
     fashioned
    0.19
     molded
    0.18
     crafted
    0.17
     stressed
    0.17
     buried
    0.17
     shattered
    0.16
     slashed
    0.16
     stretched
    0.16
     united
    0.16
     settled
    0.16
    Act Density 1.011%

    No Known Activations