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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or strategies

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing possession or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Synopsis
    -0.76
     ®
    -0.74
     UPDATE
    -0.73
     Updated
    -0.66
    ãĥ«
    -0.65
    christ
    -0.65
     Recall
    -0.65
    assis
    -0.65
    cus
    -0.65
    edition
    -0.64
    POSITIVE LOGITS
     gotta
    1.07
     tremendous
    1.05
     been
    0.97
     gonna
    0.95
     lots
    0.91
     somebody
    0.90
     definitely
    0.90
     unbelievable
    0.84
     tons
    0.84
     plenty
    0.84
    Act Density 0.269%

    No Known Activations