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

    Neuronpedia

    INDEX
    Explanations

    phrases related to film and television ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urge
    -0.17
    artner
    -0.16
    ndef
    -0.15
    hc
    -0.14
    blast
    -0.14
    andler
    -0.14
    .ol
    -0.14
    ÄIJT
    -0.14
    åij
    -0.14
    _internal
    -0.14
    POSITIVE LOGITS
    unft
    0.16
     Pickup
    0.15
    bote
    0.15
    æĪ¶
    0.14
    PROTO
    0.14
    æĪ·
    0.14
    rez
    0.13
    imuth
    0.13
    brew
    0.13
    ett
    0.13
    Act Density 0.055%

    No Known Activations