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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic degrees or titles, particularly doctorates and directorials

    oai_token-act-pair · gpt-3.5-turbo

    words related to academic degrees and formal titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.86
    rir
    -0.71
    YR
    -0.65
    avez
    -0.65
     cor
    -0.63
     lodging
    -0.62
     attm
    -0.61
     Wem
    -0.61
    ãĥ¯ãĥ³
    -0.60
     reversible
    -0.60
    POSITIVE LOGITS
    rats
    0.82
    thood
    0.80
    nesses
    0.77
    poke
    0.66
    GGGG
    0.65
    GGGGGGGG
    0.64
    gements
    0.63
    %%
    0.61
    EEE
    0.59
    icious
    0.59
    Act Density 0.183%

    No Known Activations