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

    Neuronpedia

    INDEX
    Explanations

    verbs and actions related to selection and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OFF
    -0.55
    Ups
    -0.54
    Away
    -0.54
    upon
    -0.53
    DeleteBehavior
    -0.52
    Off
    -0.52
    OUT
    -0.51
    Out
    -0.50
    Up
    -0.50
    Ons
    -0.50
    POSITIVE LOGITS
     Wikiseite
    0.54
     '\\;'
    0.45
     Moscú
    0.39
     للمعارف
    0.39
    ftagPool
    0.38
     Mittelpunkt
    0.37
     graduación
    0.37
     violación
    0.37
     civilización
    0.37
    })));
    0.36
    Act Density 0.376%

    No Known Activations