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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical locations or sites in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chl
    -0.16
    kest
    -0.15
    lore
    -0.14
    ä¿
    -0.14
    awns
    -0.14
    -syntax
    -0.14
    plex
    -0.14
    lei
    -0.13
     Mate
    -0.13
    akis
    -0.13
    POSITIVE LOGITS
    /on
    0.33
    /off
    0.30
    /out
    0.27
    /down
    0.20
    /at
    0.19
    /in
    0.18
    /by
    0.16
    ister
    0.15
    \-
    0.15
    jab
    0.15
    Act Density 0.076%

    No Known Activations