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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and interaction with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jeografia
    -0.68
    OrBuilder
    -0.65
     massif
    -0.62
    ArgsConstructor
    -0.60
    shadowRadius
    -0.59
    calips
    -0.57
     protoimpl
    -0.57
    Filmographie
    -0.57
    Atentamente
    -0.56
    FailureListener
    -0.56
    POSITIVE LOGITS
     passers
    0.59
     passer
    0.55
    UNIDENTIFIED
    0.52
    Excuse
    0.51
     pedestrians
    0.50
     membayar
    0.50
    :✨
    0.49
    ghted
    0.48
     kasarigan
    0.47
    Itoa
    0.46
    Act Density 0.267%

    No Known Activations