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

    Neuronpedia

    INDEX
    Explanations

    words related to science and technology

    oai_token-act-pair · gpt-3.5-turbo

    suffixes and morphological components of words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DERR
    -0.69
    JUST
    -0.68
    GGGGGGGG
    -0.65
    OTAL
    -0.62
     ende
    -0.62
    igers
    -0.62
    %]
    -0.58
    vertisement
    -0.58
    rots
    -0.57
    BILITIES
    -0.55
    POSITIVE LOGITS
     hybrid
    0.84
     hybrids
    0.82
     alike
    0.78
    ioned
    0.72
     syndrome
    0.71
    enced
    0.69
     complexes
    0.69
     combo
    0.67
    iated
    0.66
    heid
    0.62
    Act Density 0.326%

    No Known Activations