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

    Neuronpedia

    INDEX
    Explanations

    phrases related to logical reasoning or coherence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NCY
    -0.15
    ottie
    -0.15
    _Impl
    -0.15
    quo
    -0.14
    istrovstvÃŃ
    -0.14
    activex
    -0.13
    £i
    -0.13
    uma
    -0.13
    isposable
    -0.13
    lion
    -0.13
    POSITIVE LOGITS
     sense
    0.57
    sense
    0.40
     senses
    0.38
     sentido
    0.37
     Sense
    0.37
     sene
    0.34
     sens
    0.33
     since
    0.32
     logical
    0.31
     cents
    0.30
    Act Density 0.037%

    No Known Activations