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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing personal opinions or observations

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express various subjective feelings or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    %%
    -0.75
    éĹĺ
    -0.73
    lat
    -0.72
    units
    -0.68
     âī¡
    -0.67
     Mole
    -0.66
    vale
    -0.65
    Featured
    -0.65
    %:
    -0.65
    successfully
    -0.64
    POSITIVE LOGITS
     bitters
    1.13
     easier
    0.99
     raining
    0.98
     funny
    0.98
     gonna
    0.96
     impossible
    0.95
     surreal
    0.95
     heartbreaking
    0.95
     difficult
    0.95
     ironic
    0.94
    Act Density 0.280%

    No Known Activations