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

    Neuronpedia

    INDEX
    Explanations

    the word "following" and its variations in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Искәрмәләр
    -0.67
    ]]
    -0.67
     Burbank
    -0.66
     Asbury
    -0.66
     chistes
    -0.66
     NCC
    -0.65
     Carlsbad
    -0.65
    lust
    -0.64
     MIB
    -0.64
    )}(
    -0.63
    POSITIVE LOGITS
     Barrett
    0.81
    asList
    0.70
     Lewin
    0.66
    tiken
    0.66
    oaks
    0.64
    IActionResult
    0.63
    зви
    0.62
    builtin
    0.62
    jabi
    0.62
     vän
    0.61
    Act Density 0.020%

    No Known Activations