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

    Neuronpedia

    INDEX
    Explanations

    instances of decision-making and intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.68
    ModelAdmin
    -0.66
    ValueStyle
    -0.64
    opsida
    -0.61
    AsUp
    -0.58
    DispatchToProps
    -0.57
    цездатний
    -0.57
     Meno
    -0.56
     oeil
    -0.56
     colectiva
    -0.56
    POSITIVE LOGITS
     decided
    0.94
     decidió
    0.89
     decidieron
    0.82
    decided
    0.82
     décidé
    0.81
     decidido
    0.76
     Decided
    0.76
     opted
    0.75
     chose
    0.74
    ことにしました
    0.74
    Act Density 0.195%

    No Known Activations