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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating division between groups or contrasting ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.70
     actionMode
    -0.54
    ThroughAttribute
    -0.54
    MergeFrom
    -0.53
     कैसी
    -0.52
     onAnimation
    -0.52
    SafeMath
    -0.51
    ]")]
    -0.51
    neos
    -0.50
    extAlignment
    -0.50
    POSITIVE LOGITS
     me
    2.20
     myself
    1.96
     ourselves
    1.92
     yourself
    1.89
     himself
    1.84
     herself
    1.75
     us
    1.73
     themselves
    1.63
     YOURSELF
    1.59
    myself
    1.58
    Act Density 0.413%

    No Known Activations