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

    Neuronpedia

    INDEX
    Explanations

    references to audience or readership in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gre
    -0.16
    ts
    -0.15
    avor
    -0.15
    oken
    -0.15
    ee
    -0.15
    aine
    -0.15
    verbatim
    -0.15
    ô
    -0.14
    Ìĥ
    -0.14
    tt
    -0.14
    POSITIVE LOGITS
    hip
    0.35
    /view
    0.22
    hood
    0.21
    /list
    0.21
    HIP
    0.20
    /client
    0.19
    /watch
    0.18
     who
    0.17
    innen
    0.16
    /users
    0.16
    Act Density 0.050%

    No Known Activations