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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a high likelihood or expectation of an event occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     most
    -0.17
    δÏĮν
    -0.16
    inand
    -0.15
     somehow
    -0.15
     mappedBy
    -0.15
    immers
    -0.14
    pery
    -0.14
    IPP
    -0.14
     more
    -0.14
    aign
    -0.14
    POSITIVE LOGITS
    afa
    0.27
    acci
    0.26
     likely
    0.25
    /all
    0.25
    likely
    0.24
    arda
    0.23
     importantly
    0.22
     certainly
    0.22
     definitely
    0.22
     assured
    0.20
    Act Density 0.032%

    No Known Activations