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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a conclusion or continuation

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as such."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icular
    -0.73
    ouston
    -0.70
    IPP
    -0.70
    ARM
    -0.69
    incial
    -0.69
    Ò
    -0.68
     Polk
    -0.68
    ãĥ¯ãĥ³
    -0.67
    UNCH
    -0.66
     Lak
    -0.64
    POSITIVE LOGITS
    iated
    0.64
     resc
    0.62
     embodiments
    0.62
     treats
    0.61
     conflicts
    0.61
     surrendered
    0.60
     matters
    0.59
     constructs
    0.58
     adaptations
    0.58
     Osw
    0.58
    Act Density 0.016%

    No Known Activations