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

    Neuronpedia

    INDEX
    Explanations

    terms related to uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _HANDLE
    -0.16
    zo
    -0.16
    è¼Ķ
    -0.14
    Łèĥ½
    -0.14
     uÄŁ
    -0.14
    Bloc
    -0.14
     "\<
    -0.14
    stro
    -0.14
    lick
    -0.13
    ateria
    -0.13
    POSITIVE LOGITS
    زاÙĨ
    0.16
    omm
    0.15
    emm
    0.15
     Evet
    0.14
    tems
    0.14
    omi
    0.14
    upy
    0.14
    amm
    0.14
    æ¯ķ
    0.14
    UInt
    0.14
    Act Density 0.025%

    No Known Activations