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

    Neuronpedia

    INDEX
    Explanations

    phrases related to severing relationships or ties with entities

    oai_token-act-pair · gpt-3.5-turbo

    references to severing or cancelling relationships, agreements, or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uzzle
    -0.69
    othermal
    -0.68
    ollah
    -0.61
    PLA
    -0.61
    ogeneous
    -0.60
    osite
    -0.60
    ãĤ©
    -0.59
    inal
    -0.58
    angled
    -0.58
    ixtures
    -0.57
    POSITIVE LOGITS
     altogether
    1.81
     entirely
    1.25
     indefinitely
    1.18
     abruptly
    1.13
     prematurely
    1.07
     due
    0.97
     outright
    0.95
     forever
    0.92
     fearing
    0.91
     voluntarily
    0.89
    Act Density 0.492%

    No Known Activations