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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and expressions of possibility or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illas
    -0.17
     ä¸ĸçķĮ
    -0.16
    åĸ
    -0.16
    elor
    -0.15
    illa
    -0.15
    gressor
    -0.14
    esso
    -0.14
    ille
    -0.14
    uja
    -0.13
    èģĶ缣
    -0.13
    POSITIVE LOGITS
    981
    0.18
    ãĥ©ãĤ¤ãĥĪ
    0.15
    eldorf
    0.14
    eyh
    0.14
    OTH
    0.14
    SED
    0.13
    anders
    0.13
    uzzi
    0.13
    ][_
    0.13
    eric
    0.13
    Act Density 0.167%

    No Known Activations