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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or agreements

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating a series of actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":["
    -0.74
    scribe
    -0.71
    rain
    -0.67
    born
    -0.66
    imp
    -0.65
    tnc
    -0.64
    ridge
    -0.64
    Enlarge
    -0.63
    ity
    -0.61
    rio
    -0.60
    POSITIVE LOGITS
     lately
    1.01
    been
    0.99
    successfully
    0.99
     gotten
    0.96
     been
    0.86
    kered
    0.86
     benefited
    0.84
     countless
    0.84
     gone
    0.83
     since
    0.82
    Act Density 0.495%

    No Known Activations