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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "start" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mant
    -0.15
    IEL
    -0.14
    Into
    -0.14
    into
    -0.14
    wer
    -0.14
    ater
    -0.14
     into
    -0.14
    ysl
    -0.14
    com
    -0.13
     correspond
    -0.13
    POSITIVE LOGITS
     innoc
    0.24
     innocent
    0.20
     humble
    0.19
     hum
    0.19
     simply
    0.17
     small
    0.17
    nings
    0.17
    -simple
    0.17
     simples
    0.17
     Hum
    0.16
    Act Density 0.041%

    No Known Activations