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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes or events happening to characters or entities

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs and actions related to change or decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     therefore
    -0.68
     âĶľâĶĢâĶĢ
    -0.65
     stems
    -0.59
    inar
    -0.58
     âĶľ
    -0.58
     belongs
    -0.57
     ISO
    -0.56
    WHERE
    -0.55
    æĺ¯
    -0.54
    TPPStreamerBot
    -0.54
    POSITIVE LOGITS
     unexpectedly
    0.95
     mysteriously
    0.82
     abruptly
    0.81
     theirs
    0.79
     inexpl
    0.78
     suddenly
    0.71
     prematurely
    0.69
     unchecked
    0.65
    Reviewer
    0.65
    ickets
    0.64
    Act Density 0.649%

    No Known Activations