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

    Neuronpedia

    INDEX
    Explanations

    keywords related to data analysis or research

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "analyze" or related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.71
     Origin
    -0.65
    Merc
    -0.65
     Pupp
    -0.63
     Primordial
    -0.63
     srfAttach
    -0.61
     Legends
    -0.61
     Kelvin
    -0.61
     Panic
    -0.58
     luck
    -0.57
    POSITIVE LOGITS
    tics
    1.45
    tical
    1.41
    zing
    1.39
    sts
    1.34
    tic
    1.33
    zed
    1.26
    zers
    1.25
    zer
    1.15
    zes
    1.13
    ¸
    1.11
    Act Density 0.070%

    No Known Activations