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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or justification for feelings or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.55
    UIFont
    -0.48
    "]=
    -0.47
    ditto
    -0.45
    UIColor
    -0.39
    kil
    -0.39
    mad
    -0.39
    uks
    -0.38
    북
    -0.38
    newArrayList
    -0.37
    POSITIVE LOGITS
    Somehow
    1.11
     Somehow
    1.05
     somehow
    1.01
    GEBURTSDATUM
    0.92
    Personensuche
    0.83
     mistakenly
    0.82
     miraculously
    0.80
    culously
    0.79
     kasarigan
    0.79
    verwijspagina
    0.79
    Act Density 0.213%

    No Known Activations