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

    Neuronpedia

    INDEX
    Explanations

    words related to affirmation, certainty, and evaluation of various situations, possibly involving a judgment or opinion

    oai_token-act-pair · gpt-3.5-turbo

    auxiliary verbs and expressions of existence or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pione
    -0.61
    GoldMagikarp
    -0.59
    iencies
    -0.56
    umbn
    -0.55
    izont
    -0.55
    ü
    -0.54
    ù
    -0.54
    é¾įå¥
    -0.54
    ē
    -0.54
    Ĝ
    -0.54
    POSITIVE LOGITS
    .
    1.71
    !.
    1.53
    .]
    1.40
    .","
    1.39
    .(
    1.38
    !
    1.37
    .[
    1.36
    .</
    1.33
    .<
    1.31
    .�
    1.31
    Act Density 0.704%

    No Known Activations