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

    Neuronpedia

    INDEX
    Explanations

    references to specific researchers and their work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.96
    mathscr
    -0.89
    ležit
    -0.87
     Mili
    -0.83
    RequestContext
    -0.83
    +#+#
    -0.83
    Christy
    -0.81
     Magdal
    -0.77
    Bridget
    -0.75
    bastian
    -0.75
    POSITIVE LOGITS
    Buk
    0.83
     Lugo
    0.81
     Buxton
    0.80
    fone
    0.80
     Cobra
    0.77
     Felice
    0.76
    rostis
    0.76
     Buk
    0.74
     Irina
    0.74
    Ches
    0.73
    Act Density 0.881%

    No Known Activations