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

    Neuronpedia

    INDEX
    Explanations

    instances of direct address and personal expression in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ready
    -0.15
    elling
    -0.14
     rol
    -0.13
    IEW
    -0.13
    mos
    -0.13
    -neck
    -0.13
     experience
    -0.13
    ified
    -0.13
     Tu
    -0.13
    _ARGUMENT
    -0.13
    POSITIVE LOGITS
     pig
    0.17
    pig
    0.16
     say
    0.15
     echo
    0.15
    Share
    0.15
     share
    0.15
    getField
    0.15
     bullet
    0.15
    Echo
    0.15
    extends
    0.14
    Act Density 0.066%

    No Known Activations