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

    Neuronpedia

    INDEX
    Explanations

    the frequency and usage of personal pronouns and variations of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥŃãĥ³
    -0.16
    ragen
    -0.15
    ellas
    -0.15
    Delegate
    -0.15
    irma
    -0.14
    ackbar
    -0.14
    arshal
    -0.14
    undy
    -0.14
    ritte
    -0.13
     dÃłnh
    -0.13
    POSITIVE LOGITS
    linger
    0.15
    lify
    0.14
    inar
    0.14
    ignon
    0.14
     indeed
    0.14
    ¥IJ
    0.14
    tingham
    0.13
     unloaded
    0.13
     introducing
    0.13
    bé
    0.13
    Act Density 0.004%

    No Known Activations