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

    Neuronpedia

    INDEX
    Explanations

    phrases related to limitations or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    statements about restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eele
    -0.77
    kinson
    -0.71
     Viz
    -0.63
    kins
    -0.62
    urat
    -0.60
     hurd
    -0.59
     installments
    -0.59
     heading
    -0.56
    aii
    -0.56
    ffield
    -0.55
    POSITIVE LOGITS
     nor
    1.19
    except
    1.18
     whatsoever
    1.10
    nor
    1.08
     except
    1.02
    no
    0.99
    nothing
    0.97
    yet
    0.97
    Neither
    0.94
    Nor
    0.90
    Act Density 0.346%

    No Known Activations