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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word 'Word' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asser
    -0.16
    /***************************************************************************↵
    -0.15
    ikh
    -0.15
    apg
    -0.14
    BUS
    -0.14
    ault
    -0.14
    ContentLoaded
    -0.14
    _words
    -0.14
     Slater
    -0.14
    mino
    -0.13
    POSITIVE LOGITS
    Perfect
    0.20
    robe
    0.19
    press
    0.19
    perfect
    0.18
    wide
    0.18
    processors
    0.17
    processor
    0.17
    wrap
    0.17
    y
    0.17
    Smith
    0.16
    Act Density 0.011%

    No Known Activations