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

    Neuronpedia

    INDEX
    Explanations

    phrases related to continuations or lists of items

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply ongoing or continuous actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lau
    -0.61
     Jiu
    -0.61
     RIS
    -0.61
     Lemon
    -0.60
     TIM
    -0.59
     Lov
    -0.58
     Promise
    -0.57
     EFF
    -0.56
     HOUSE
    -0.55
     Pan
    -0.55
    POSITIVE LOGITS
    .,
    0.98
    .?
    0.91
    .;
    0.90
    .--
    0.86
    eter
    0.85
    .:
    0.83
    .—
    0.81
    )=(
    0.80
    .
    0.79
    ãĢĤ
    0.79
    Act Density 0.054%

    No Known Activations