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

    Neuronpedia

    INDEX
    Explanations

    references to authorship and literary analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oku
    -0.17
    çĶ
    -0.15
    äºľ
    -0.14
    fx
    -0.14
    RTL
    -0.14
     Speed
    -0.14
     NAS
    -0.13
    MAS
    -0.13
    -0.13
     Fuck
    -0.13
    POSITIVE LOGITS
     texts
    0.18
    texts
    0.16
     securely
    0.16
    Margins
    0.15
     textual
    0.15
    /text
    0.15
     Registers
    0.15
    early
    0.15
     misog
    0.15
     dossier
    0.14
    Act Density 0.078%

    No Known Activations