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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating obviousness or clarity in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elman
    -0.20
    ery
    -0.16
    ERY
    -0.15
    quist
    -0.14
    orable
    -0.14
    istrovstvÃŃ
    -0.14
    ë¿IJ
    -0.14
    quette
    -0.14
    hape
    -0.14
    CKER
    -0.14
    POSITIVE LOGITS
    ively
    0.16
    mente
    0.15
    çĦ¶
    0.15
    anco
    0.15
    urer
    0.15
    aneously
    0.14
    -cut
    0.14
     rÃłng
    0.14
    ly
    0.14
    eye
    0.14
    Act Density 0.056%

    No Known Activations