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

    Neuronpedia

    INDEX
    Explanations

    terms related to various philosophical and ideological categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    太éĥİ
    -0.15
    -earth
    -0.14
    ovi
    -0.13
    lectual
    -0.13
    eya
    -0.13
     eff
    -0.13
    itol
    -0.13
     Buckley
    -0.13
    GN
    -0.13
    ello
    -0.13
    POSITIVE LOGITS
    velle
    0.14
    ména
    0.14
    дап
    0.14
    ovu
    0.14
    .bio
    0.13
    /Foundation
    0.13
    åħį
    0.13
    aran
    0.13
    aceae
    0.13
    _listener
    0.13
    Act Density 0.043%

    No Known Activations