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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intention or direction towards actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentAsync
    -0.81
     feroit
    -0.75
     pinulongan
    -0.72
     deportivos
    -0.69
    complexContent
    -0.67
     exécut
    -0.67
     ComVisible
    -0.66
     judiciales
    -0.66
    -0.65
     morire
    -0.65
    POSITIVE LOGITS
     Way
    0.70
     ways
    0.63
     way
    0.61
    Way
    0.57
     طريقة
    0.55
    Ways
    0.54
     WAYS
    0.54
    辦法
    0.53
    ByDefault
    0.52
     WAY
    0.52
    Act Density 0.131%

    No Known Activations