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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating increased intensity or action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "step up" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.73
    puted
    -0.73
     Crate
    -0.68
    ogg
    -0.67
    ãĥĥãĥī
    -0.66
     Horus
    -0.65
    oyer
    -0.63
    士
    -0.61
    thing
    -0.61
    SourceFile
    -0.61
    POSITIVE LOGITS
     pressure
    1.13
     efforts
    1.12
     patrols
    1.11
     scrutiny
    1.06
     preparations
    0.98
     vigilance
    0.98
     intensity
    0.95
    pressure
    0.95
     lobbying
    0.91
     hostilities
    0.90
    Act Density 0.098%

    No Known Activations