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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "nothing" followed by the phrase "more" and a verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of negation or minimalism in expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.90
     [|
    -0.71
    church
    -0.68
     Pengu
    -0.63
    aii
    -0.63
    ivas
    -0.61
    sten
    -0.60
    visor
    -0.60
    ppel
    -0.60
     Elements
    -0.59
    POSITIVE LOGITS
     except
    0.96
    except
    0.84
     whatsoever
    0.83
     transpired
    0.73
    pires
    0.72
     resembling
    0.72
    Except
    0.70
     besides
    0.69
     happening
    0.66
     stopping
    0.58
    Act Density 0.166%

    No Known Activations