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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or resignation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PageContext
    -0.75
     plak
    -0.71
     Walkover
    -0.71
    ()}>
    -0.66
    avía
    -0.65
     straws
    -0.65
     HttpNotFound
    -0.65
    </tr>
    -0.64
    CloseOperation
    -0.64
    AsUp
    -0.64
    POSITIVE LOGITS
     يتيمه
    0.81
    poptosis
    0.79
     Im
    0.77
     preghiera
    0.77
    west
    0.74
     forhold
    0.72
    enerbah
    0.72
     attiv
    0.72
     nyug
    0.71
    Pele
    0.71
    Act Density 0.149%

    No Known Activations