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

    Neuronpedia

    INDEX
    Explanations

    words related to actions of processing, manipulating, or managing data and objects

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

    past tense verbs ending in -ed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.77
     houſe
    -0.75
     ſche
    -0.68
     purpoſe
    -0.66
     Houſe
    -0.65
    ſelf
    -0.61
     ſtate
    -0.60
     ſch
    -0.59
     reaſon
    -0.57
     ſtre
    -0.56
    POSITIVE LOGITS
    aced
    0.94
    ourced
    0.86
    iked
    0.86
    tered
    0.84
    ricted
    0.82
    rayed
    0.82
    tituted
    0.82
    ched
    0.82
    lified
    0.82
    cated
    0.80
    Act Density 1.798%

    No Known Activations