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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "write" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -2.01
    <?
    -0.66
    ⓧ
    -0.64
    dom
    -0.61
     nad
    -0.60
    stamo
    -0.59
    ev
    -0.58
    Traducción
    -0.57
    ProgressHUD
    -0.56
    ട
    -0.55
    POSITIVE LOGITS
     maneu
    1.75
     Minang
    1.63
     impra
    1.61
     unspeak
    1.56
     increa
    1.56
     disagre
    1.54
     disreg
    1.53
     reluct
    1.52
     apprehen
    1.51
     disgra
    1.50
    Act Density 0.156%

    No Known Activations