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

    Neuronpedia

    INDEX
    Explanations

    the term "most" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pery
    -0.16
    δÏĮν
    -0.16
    atori
    -0.15
     nice
    -0.15
    amilia
    -0.14
    ams
    -0.14
    AMS
    -0.14
     mappedBy
    -0.14
     Campos
    -0.14
    iously
    -0.14
    POSITIVE LOGITS
    acci
    0.24
    afa
    0.23
    arda
    0.22
     definitely
    0.21
     importantly
    0.20
    ecká
    0.20
     certainly
    0.19
     Wanted
    0.18
    efa
    0.17
     Definitely
    0.17
    Act Density 0.034%

    No Known Activations