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

    Neuronpedia

    INDEX
    Explanations

    terms related to literary or academic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .mods
    -0.15
    enna
    -0.14
    is
    -0.14
     Fountain
    -0.14
    eko
    -0.14
    chrift
    -0.14
    igy
    -0.14
     sob
    -0.14
    inja
    -0.14
    raya
    -0.14
    POSITIVE LOGITS
    amenti
    0.31
    amento
    0.21
    aci
    0.17
    anzi
    0.16
    ati
    0.16
    amentos
    0.16
    gio
    0.15
    adin
    0.15
    ami
    0.15
    arsi
    0.15
    Act Density 0.002%

    No Known Activations