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

    Neuronpedia

    INDEX
    Explanations

    words related to information gathering and investigation

    oai_token-act-pair · gpt-3.5-turbo

    references to sensory experiences and physical interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.85
    bral
    -0.69
    uers
    -0.65
    luaj
    -0.60
    rers
    -0.60
    adr
    -0.58
    united
    -0.57
     negotiators
    -0.55
     Amar
    -0.55
    Loading
    -0.54
    POSITIVE LOGITS
     imaginable
    1.22
     whatsoever
    1.17
     except
    1.17
    except
    0.91
    soever
    0.85
     irrespective
    0.84
     regardless
    0.83
     thereafter
    0.78
     MUST
    0.77
     conceivable
    0.76
    Act Density 0.659%

    No Known Activations