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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal challenges and inequalities experienced by marginalized groups

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    OGND
    -0.53
    principalColumn
    -0.51
    DataAnnotations
    -0.49
    SPATH
    -0.48
    HideFlags
    -0.48
     aceptas
    -0.48
     VIDEOTAPE
    -0.48
    ValueGeneration
    -0.47
    kloped
    -0.47
    Geplaatst
    -0.46
    POSITIVE LOGITS
     яко
    0.63
     supuestamente
    0.61
     somehow
    0.61
    __*/
    0.59
    bukkit
    0.58
     supposedly
    0.58
     mxArray
    0.57
     angeb
    0.52
     magically
    0.51
    orithmic
    0.50
    Act Density 0.551%

    No Known Activations