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

    Neuronpedia

    INDEX
    Explanations

    specific terms or phrases related to various topics mixed with general words and names

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to social issues and cultural commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.63
    ependence
    -0.63
    endas
    -0.62
     Flavoring
    -0.59
    thood
    -0.58
    rities
    -0.58
    ¬¼
    -0.58
    ãĥ´
    -0.58
    ibus
    -0.57
    Ru
    -0.57
    POSITIVE LOGITS
    PLIED
    0.76
    vable
    0.73
     liable
    0.72
     incarn
    0.70
    adj
    0.68
     unto
    0.68
     anyway
    0.66
     certified
    0.65
    opped
    0.65
     soluble
    0.64
    Act Density 0.946%

    No Known Activations