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

    Neuronpedia

    INDEX
    Explanations

    action-oriented phrases or statements containing the word "always."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate ongoing actions or continual states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bia
    -0.62
    ·
    -0.61
    ettlement
    -0.61
    ģ«
    -0.59
    ALLY
    -0.59
    VICE
    -0.58
     presently
    -0.58
    Yang
    -0.58
    dm
    -0.57
    NAME
    -0.57
    POSITIVE LOGITS
    ailable
    0.73
    ministic
    0.70
    ounters
    0.70
    andro
    0.67
    oin
    0.67
     pursu
    0.67
    rences
    0.66
    enos
    0.65
    dule
    0.65
    theless
    0.64
    Act Density 0.181%

    No Known Activations