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

    Neuronpedia

    INDEX
    Explanations

    phrases or statements that indicate strong emotions or significant moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    locker
    -0.16
    ardy
    -0.15
    olah
    -0.15
    shiv
    -0.15
    ZONE
    -0.14
    мÑĭ
    -0.14
    CHandle
    -0.14
    opoulos
    -0.14
    aille
    -0.14
    393
    -0.14
    POSITIVE LOGITS
    olds
    0.16
     kå
    0.15
    éĥ
    0.15
    esis
    0.14
    swer
    0.14
     slammed
    0.14
    tal
    0.14
    activated
    0.14
    790
    0.14
    ãĥ¼ãĥĵ
    0.14
    Act Density 0.257%

    No Known Activations