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

    Neuronpedia

    INDEX
    Explanations

    attempts and actions related to persuasion, understanding, and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Futura
    -0.76
     useAuth
    -0.67
    glow
    -0.66
    styleType
    -0.60
     constaté
    -0.60
     Flores
    -0.59
     höchst
    -0.58
     Palacios
    -0.58
    IBarButtonItem
    -0.56
     keş
    -0.55
    POSITIVE LOGITS
     attempts
    1.11
     attempt
    1.09
     versucht
    1.03
     tries
    1.00
    Attempts
    0.96
     Trying
    0.95
     Attempt
    0.95
     Attempts
    0.95
     tryna
    0.94
     versuchen
    0.93
    Act Density 0.142%

    No Known Activations