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

    Neuronpedia

    INDEX
    Explanations

    comparative terms and quantities

    oai_token-act-pair · gpt-3.5-turbo

    repetitive structures highlighting increasing quantities or frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è£
    -0.71
    ãĤ´ãĥ³
    -0.70
    æ©
    -0.70
    although
    -0.67
    Vel
    -0.67
    çī
    -0.66
    VERTISEMENT
    -0.65
    borg
    -0.65
    REE
    -0.64
    Ò
    -0.63
    POSITIVE LOGITS
     you
    0.67
    ratulations
    0.66
     educated
    0.65
     fortunate
    0.65
     prevalent
    0.64
     embodiment
    0.61
     vibrations
    0.61
     mature
    0.60
     matured
    0.60
     optimistic
    0.60
    Act Density 0.054%

    No Known Activations