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

    Neuronpedia

    INDEX
    Explanations

    frequent or significant words that indicate expectations or obligations within a textual context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pector
    -0.19
    esar
    -0.17
    awks
    -0.16
     à¤¬à¤ľ
    -0.15
    icom
    -0.15
    ̣
    -0.15
     ab
    -0.15
     fin
    -0.15
    adders
    -0.15
    alling
    -0.14
    POSITIVE LOGITS
    ount
    0.17
    âĹıâĹı
    0.15
    icha
    0.15
     Aura
    0.15
    ROUT
    0.15
    angi
    0.15
     Inner
    0.15
    $MESS
    0.14
    versible
    0.14
    ewis
    0.14
    Act Density 0.005%

    No Known Activations