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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of guidelines or discussion on specific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.65
     snippetHide
    -0.60
     myſelf
    -0.58
    OrBuilder
    -0.57
     ***!
    -0.57
    quelize
    -0.57
    nastics
    -0.56
    ividual
    -0.56
    ſelf
    -0.56
    tvguidetime
    -0.55
    POSITIVE LOGITS
    GEBURTSDATUM
    0.56
     yet
    0.56
     proper
    0.53
     properly
    0.52
    TargetException
    0.49
     affatto
    0.47
     actually
    0.46
     Yet
    0.45
    Ada
    0.44
    Yet
    0.44
    Act Density 1.132%

    No Known Activations