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

    Neuronpedia

    INDEX
    Explanations

    issues related to problem-solving in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flesta
    -0.80
     heureuse
    -0.70
     verksamhet
    -0.66
     réguli
    -0.66
     feroit
    -0.64
     uſed
    -0.63
     quæ
    -0.63
     avoient
    -0.63
     attiva
    -0.62
     femininas
    -0.62
    POSITIVE LOGITS
     lack
    1.16
     whether
    1.04
     timing
    0.93
     how
    0.89
    lack
    0.85
     fehl
    0.84
    如何
    0.82
     Lack
    0.82
    会不会
    0.81
    whether
    0.80
    Act Density 0.448%

    No Known Activations