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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to consequences and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <>",
    -0.50
    (())
    -0.47
    SequentialGroup
    -0.47
    (||
    -0.45
    waitKey
    -0.43
     actualmente
    -0.43
    millan
    -0.43
    ifflin
    -0.42
    protoimpl
    -0.41
    spire
    -0.41
    POSITIVE LOGITS
    Portail
    0.67
    GEBURTSDATUM
    0.65
    fucking
    0.65
     fuckin
    0.64
     gonna
    0.60
    Cyfeiriadau
    0.60
     NSCoder
    0.59
     assolutamente
    0.58
     gotta
    0.58
     EVERYTHING
    0.57
    Act Density 0.067%

    No Known Activations