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

    Neuronpedia

    INDEX
    Explanations

    the word "as" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    evice
    -0.19
    erken
    -0.16
    enci
    -0.16
     à¤īसस
    -0.15
    rello
    -0.15
    mens
    -0.14
    gles
    -0.14
    ayas
    -0.14
    vla
    -0.14
    ãĢħ
    -0.14
    POSITIVE LOGITS
     they
    0.32
     soon
    0.26
     we
    0.26
    they
    0.21
     åIJĦ
    0.20
    /if
    0.20
     she
    0.19
     you
    0.19
     each
    0.19
     various
    0.19
    Act Density 0.092%

    No Known Activations