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

    Neuronpedia

    INDEX
    Explanations

    instances of the preposition "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cald
    -0.19
    ONA
    -0.16
    oil
    -0.15
    uzzi
    -0.14
    ossa
    -0.14
    inas
    -0.13
     Tradition
    -0.13
    neau
    -0.13
    ugas
    -0.13
    wy
    -0.13
    POSITIVE LOGITS
     daemon
    0.17
    shal
    0.17
    UTH
    0.16
    836
    0.14
    eriod
    0.14
     Geographic
    0.14
    OX
    0.14
    коз
    0.14
    gesch
    0.14
    iggers
    0.14
    Act Density 0.028%

    No Known Activations