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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "as" used for comparisons or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    klad
    -0.15
    added
    -0.15
    uded
    -0.15
    ÑĨÑĮ
    -0.15
    itches
    -0.14
    ointed
    -0.14
    onda
    -0.14
    ahn
    -0.14
    Aligned
    -0.14
    ohn
    -0.14
    POSITIVE LOGITS
    -is
    0.31
     intended
    0.27
     written
    0.22
     originally
    0.22
     planned
    0.21
     designed
    0.20
    _is
    0.20
     Is
    0.19
    .is
    0.17
     expected
    0.17
    Act Density 0.077%

    No Known Activations