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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate caution, skepticism, or the act of stating something is not true

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eper
    -0.14
    ascal
    -0.14
     Schwarz
    -0.14
    gaard
    -0.13
     scissors
    -0.13
    713
    -0.13
     rej
    -0.13
     ÃŃ
    -0.13
     Angebot
    -0.13
     silly
    -0.13
    POSITIVE LOGITS
    eyJ
    0.18
    ahlen
    0.15
    -animate
    0.14
    VL
    0.14
    obl
    0.14
    razier
    0.14
    isos
    0.14
    é»
    0.14
    OLON
    0.14
    BOSE
    0.14
    Act Density 0.095%

    No Known Activations