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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to objectives or goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RTHOOK
    -0.52
    ItemBackground
    -0.44
     isKindOfClass
    -0.44
    rativa
    -0.44
    inSlope
    -0.43
     setStatus
    -0.43
    tiéndose
    -0.40
    paganda
    -0.40
    esity
    -0.40
    outSlope
    -0.39
    POSITIVE LOGITS
     objective
    1.01
    objective
    0.77
     core
    0.77
     goal
    0.76
     aim
    0.76
     objetivo
    0.68
    objectif
    0.65
     obiettivo
    0.65
     objectif
    0.63
    Core
    0.60
    Act Density 0.577%

    No Known Activations