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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve actions, particularly those indicating potential outcomes or transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addGap
    -0.57
    UnusedPrivate
    -0.56
     preferred
    -0.50
    jsxFileName
    -0.49
     ValueError
    -0.48
     conhe
    -0.48
    각주
    -0.46
    SequentialGroup
    -0.46
     hoogte
    -0.45
    if
    -0.44
    POSITIVE LOGITS
     propOrder
    0.67
    eroon
    0.63
    MessageOf
    0.61
    󠁧
    0.60
    chemia
    0.58
    AndEndTag
    0.57
     kwanza
    0.57
    oxone
    0.57
    THING
    0.56
    ddots
    0.56
    Act Density 0.288%

    No Known Activations