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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and dialogue

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, primarily commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesday
    -0.79
     corrid
    -0.72
    swick
    -0.72
    ilst
    -0.70
    æ©
    -0.68
    lead
    -0.65
    uces
    -0.63
    cuts
    -0.62
    oes
    -0.61
    ãĥ¯ãĥ³
    -0.61
    POSITIVE LOGITS
     undeniably
    0.68
     uh
    0.67
     Borough
    0.67
     alas
    0.67
     biologically
    0.66
     aest
    0.64
    yet
    0.64
    atown
    0.64
     barring
    0.63
    velength
    0.62
    Act Density 0.133%

    No Known Activations