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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the absence of proper authorization or legitimacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lyon
    -0.16
    romatic
    -0.15
    arton
    -0.14
    á»ĵ
    -0.14
    CursorPosition
    -0.14
    боÑĤ
    -0.14
    urr
    -0.14
    eno
    -0.13
    rum
    -0.13
    _NOW
    -0.13
    POSITIVE LOGITS
     justify
    0.22
     justification
    0.22
    justify
    0.18
     reason
    0.17
    reason
    0.17
     justified
    0.16
     vet
    0.16
     reasons
    0.16
     correspond
    0.16
     rationale
    0.16
    Act Density 0.147%

    No Known Activations