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

    Neuronpedia

    INDEX
    Explanations

    words related to the establishment or foundation of programs and initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SCO
    -0.14
    ederal
    -0.14
    avaÅŁ
    -0.14
    plet
    -0.13
    edom
    -0.13
     ogs
    -0.13
    layers
    -0.13
    ship
    -0.13
    umont
    -0.13
    /signup
    -0.13
    POSITIVE LOGITS
    jango
    0.15
    hend
    0.14
    stad
    0.14
    jekt
    0.14
    eltas
    0.13
     Haram
    0.13
     INLINE
    0.13
    ÙĪرÛĮ
    0.13
    ync
    0.13
    efe
    0.13
    Act Density 0.082%

    No Known Activations