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

    Neuronpedia

    INDEX
    Explanations

    indicators of absence or lack of things

    oai_token-act-pair · gpt-3.5-turbo

    statements that emphasize a lack of resources or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eele
    -0.77
    veland
    -0.65
    avis
    -0.65
    kinson
    -0.64
    uce
    -0.63
    enge
    -0.62
    imb
    -0.62
    eco
    -0.61
    ef
    -0.61
    abre
    -0.61
    POSITIVE LOGITS
     nothing
    1.34
    nothing
    1.31
     no
    1.28
     none
    1.24
    no
    1.17
     nor
    1.16
    nor
    1.14
     nobody
    1.14
    except
    1.13
     whatsoever
    1.10
    Act Density 0.236%

    No Known Activations