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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or occurrence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "often" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.81
    ENE
    -0.72
    agate
    -0.71
    imming
    -0.68
    jri
    -0.68
     Integrity
    -0.67
    gewater
    -0.67
    shi
    -0.66
    anmar
    -0.65
    ablishment
    -0.65
    POSITIVE LOGITS
    entimes
    1.45
    theless
    1.10
    times
    0.98
     times
    0.95
     overlooked
    0.92
    rences
    0.81
    Used
    0.81
     mistaken
    0.80
     resorted
    0.80
     Asked
    0.79
    Act Density 0.034%

    No Known Activations