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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing certainty or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the presence of non-text content or formatting cues in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illary
    -0.80
    cffff
    -0.65
    omore
    -0.65
    ËĪ
    -0.64
    icipated
    -0.64
    rift
    -0.64
    aded
    -0.62
    ¥ŀ
    -0.62
    ategory
    -0.60
    mone
    -0.59
    POSITIVE LOGITS
    esley
    0.93
    come
    0.89
     hello
    0.89
     guess
    0.88
    ington
    0.86
     congratulations
    0.86
     yeah
    0.85
    tons
    0.81
    spring
    0.80
    adays
    0.80
    Act Density 0.027%

    No Known Activations