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

    Neuronpedia

    INDEX
    Explanations

    key terms related to decision-making and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     {:.
    -0.71
     getF
    -0.68
    énario
    -0.68
    Warm
    -0.66
     Warm
    -0.63
    déric
    -0.63
    missive
    -0.63
    illah
    -0.62
    WARM
    -0.62
     getM
    -0.62
    POSITIVE LOGITS
     with
    0.72
     on
    0.68
    ViewFeatures
    0.67
     in
    0.66
     from
    0.63
     to
    0.60
     again
    0.58
     at
    0.56
     through
    0.56
     similar
    0.55
    Act Density 0.825%

    No Known Activations