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

    Neuronpedia

    INDEX
    Explanations

    instances of words or verb forms related to actions or processes that are ongoing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the substring "ing" appearing at the end of words or as part of word tokens.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     laiko
    -0.36
     comerciais
    -0.35
     lumières
    -0.34
     voren
    -0.34
     själ
    -0.34
     woda
    -0.33
     inhoud
    -0.33
     portátiles
    -0.33
     behalf
    -0.33
     mezzi
    -0.33
    POSITIVE LOGITS
     informée
    0.58
    interopRequire
    0.57
    AddTagHelper
    0.54
    WriteTagHelper
    0.53
    hetti
    0.53
     LING
    0.53
    WriteBarrier
    0.52
    estion
    0.51
    expandindo
    0.51
    MemoryWarning
    0.51
    Act Density 0.239%

    No Known Activations