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

    Neuronpedia

    INDEX
    Explanations

    contractions with 's

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "it’s" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nel
    -0.78
    DS
    -0.73
    ESE
    -0.72
    %%
    -0.70
    ievers
    -0.70
    igraph
    -0.69
    roit
    -0.68
    soever
    -0.67
    ollow
    -0.67
    INST
    -0.66
    POSITIVE LOGITS
     been
    1.39
     gotta
    1.32
     gotten
    1.21
     got
    1.14
     gonna
    1.11
     unclear
    1.08
    been
    1.02
     doubtful
    0.98
     conceivable
    0.97
     impossible
    0.97
    Act Density 0.121%

    No Known Activations