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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating desire and the ability to achieve specific outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ClassPath
    -0.60
    نص
    -0.58
    AndEndTag
    -0.57
     verg
    -0.50
    BeginContext
    -0.49
    Tembelea
    -0.48
     yourself
    -0.47
    ftagPool
    -0.47
    tsy
    -0.46
     Yourself
    -0.46
    POSITIVE LOGITS
     needed
    1.18
    needed
    1.14
     Needed
    1.10
     desired
    1.01
    Needed
    0.95
     NEEDED
    0.94
    desired
    0.94
     necessary
    0.93
     requisite
    0.93
     required
    0.88
    Act Density 0.289%

    No Known Activations