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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize or identify specific examples or cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orman
    -0.19
    ensch
    -0.17
     such
    -0.16
    ungs
    -0.14
     Such
    -0.14
    ict
    -0.14
    orque
    -0.13
    ât
    -0.13
    ager
    -0.13
    idental
    -0.13
    POSITIVE LOGITS
    like
    0.18
    -ÑĤо
    0.18
     things
    0.18
    ìłĢ
    0.17
     ÑģобÑĸ
    0.16
    -called
    0.15
    ily
    0.15
    curity
    0.15
     coisa
    0.15
     воÑĤ
    0.15
    Act Density 0.052%

    No Known Activations