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

    Neuronpedia

    INDEX
    Explanations

    the presence of the start token in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.74
    awtextra
    -0.68
     queſta
    -0.67
     setEmail
    -0.66
     ExecuteAsync
    -0.66
     TType
    -0.66
    pecabe
    -0.65
    enterOuterAlt
    -0.64
     snippetHide
    -0.64
    KommentareTeilen
    -0.64
    POSITIVE LOGITS
    <blockquote>
    0.52
     "
    0.37
     Steinberg
    0.35
    ?
    0.34
     Brunnen
    0.33
     Guild
    0.32
     “
    0.31
    ad
    0.31
    "]();
    0.31
    agu
    0.31
    Act Density 0.050%

    No Known Activations