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

    Neuronpedia

    INDEX
    Explanations

    sentences with words related to communication and interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of human interaction and the uniqueness of individual experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rers
    -0.71
    bral
    -0.71
    rer
    -0.68
    ahime
    -0.64
    reements
    -0.59
    emn
    -0.57
    uers
    -0.57
     negotiators
    -0.56
     respectively
    -0.56
    cients
    -0.54
    POSITIVE LOGITS
     imaginable
    1.22
     whatsoever
    1.13
    soever
    1.07
     except
    1.06
    pires
    0.87
     anywhere
    0.83
    except
    0.82
     irrespective
    0.82
     regardless
    0.81
     MUST
    0.80
    Act Density 0.653%

    No Known Activations