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

    Neuronpedia

    INDEX
    Explanations

    adverbs that indicate frequency or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    frequency or conditional likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informations
    -0.33
    nameof
    -0.31
     ADMINISTR
    -0.30
     Watch
    -0.29
     tels
    -0.29
     hú
    -0.28
     infor
    -0.27
     administrators
    -0.27
     aliments
    -0.27
     According
    -0.26
    POSITIVE LOGITS
     Geſch
    0.84
     Geiſt
    0.81
     beſte
    0.77
    __*/
    0.75
     Waſſer
    0.75
     deſſen
    0.74
     vooz
    0.74
    niſſe
    0.74
    ſchaft
    0.72
     müſſen
    0.71
    Act Density 0.065%

    No Known Activations