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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or progression

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "going" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ament
    -0.74
    ullah
    -0.69
    rika
    -0.69
    aments
    -0.67
    ividually
    -0.64
    ribution
    -0.64
     likelihood
    -0.61
    itionally
    -0.61
    ritional
    -0.61
     resultant
    -0.59
    POSITIVE LOGITS
     overboard
    1.12
     extinct
    1.01
     viral
    0.97
     downhill
    0.91
    vt
    0.89
    ggle
    0.87
     crazy
    0.86
     bye
    0.86
     nuts
    0.85
     Klux
    0.82
    Act Density 0.076%

    No Known Activations