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

    Neuronpedia

    INDEX
    Explanations

    references to "lower" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     higher
    -0.19
    ute
    -0.19
    aml
    -0.17
     little
    -0.16
     Higher
    -0.15
     Svens
    -0.15
     above
    -0.15
    ift
    -0.15
    unk
    -0.14
    ÑĤеÑĢи
    -0.14
    POSITIVE LOGITS
    cased
    0.22
    -than
    0.22
    most
    0.21
    archy
    0.21
    anging
    0.20
    Than
    0.20
    -middle
    0.20
    _than
    0.20
    -priced
    0.18
    case
    0.18
    Act Density 0.028%

    No Known Activations