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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or conditions that indicate dependency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ughty
    -0.16
    osing
    -0.15
    polator
    -0.15
    ila
    -0.15
    058
    -0.14
    اÙĨÛĮ
    -0.14
     transc
    -0.14
    ÅĻila
    -0.14
    olk
    -0.14
    arium
    -0.14
    POSITIVE LOGITS
    adata
    0.17
    dealloc
    0.15
    owell
    0.15
    ÑģÑĤиÑĩ
    0.15
     speech
    0.15
    atr
    0.14
    ission
    0.14
    çĶ
    0.14
    ãĤ¹ãĥĨ
    0.14
    Chi
    0.14
    Act Density 0.010%

    No Known Activations