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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb 'to be' and their various conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sel
    -0.17
    dre
    -0.16
    ninger
    -0.16
    umbo
    -0.16
    ãĥ¼ãĥį
    -0.15
    dy
    -0.15
    istro
    -0.14
    die
    -0.14
    occo
    -0.14
    rov
    -0.14
    POSITIVE LOGITS
    quest
    0.27
    ized
    0.25
    izing
    0.25
    em
    0.24
    paration
    0.24
    eming
    0.23
    ething
    0.23
    par
    0.23
    ize
    0.22
    parate
    0.22
    Act Density 0.014%

    No Known Activations