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

    Neuronpedia

    INDEX
    Explanations

    phrases and references related to uncertainty and unknown conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irim
    -0.16
    267
    -0.14
    Wrong
    -0.14
    ÏĦαÏĤ
    -0.14
    adden
    -0.14
    ruba
    -0.14
    ORED
    -0.14
    outil
    -0.14
    FALSE
    -0.14
    rzy
    -0.14
    POSITIVE LOGITS
     unknown
    0.58
    unknown
    0.47
     Unknown
    0.46
     unclear
    0.45
     UNKNOWN
    0.44
     uncertain
    0.43
    Unknown
    0.42
    _unknown
    0.38
     mystery
    0.38
    UNKNOWN
    0.36
    Act Density 0.261%

    No Known Activations