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

    Neuronpedia

    INDEX
    Explanations

    words related to entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itat
    -0.16
    cene
    -0.16
    deen
    -0.15
    ONTAL
    -0.15
     McCart
    -0.15
    enate
    -0.15
    ACKET
    -0.14
    ucc
    -0.14
    ULO
    -0.14
    itra
    -0.14
    POSITIVE LOGITS
    ament
    0.15
    vo
    0.14
    aiser
    0.14
     predictable
    0.14
    ίθ
    0.14
    ening
    0.14
     Suns
    0.14
    Ãłm
    0.14
    993
    0.13
    quette
    0.13
    Act Density 0.000%

    No Known Activations