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

    Neuronpedia

    INDEX
    Explanations

    words related to tangible objects and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ABLE
    -0.16
     Truy
    -0.16
    ted
    -0.15
    ned
    -0.15
    IZE
    -0.14
    ypical
    -0.14
    acey
    -0.13
    ierte
    -0.13
    oze
    -0.13
    ServiceImpl
    -0.13
    POSITIVE LOGITS
    als
    0.17
    icon
    0.15
    us
    0.15
    remen
    0.15
    igo
    0.15
    il
    0.15
    oris
    0.15
    akes
    0.15
    776
    0.14
    ereum
    0.14
    Act Density 0.901%

    No Known Activations