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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating instructions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating necessity or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IoT
    -0.70
     Miko
    -0.70
    ahime
    -0.67
     [|
    -0.64
    uum
    -0.63
     Pengu
    -0.61
     Oak
    -0.61
    ews
    -0.60
     Mori
    -0.58
     IEEE
    -0.57
    POSITIVE LOGITS
    illion
    0.81
     toget
    0.69
     besides
    0.69
     except
    0.68
     save
    0.68
    herer
    0.68
    ="#
    0.67
    soever
    0.66
    can
    0.64
    Ever
    0.63
    Act Density 0.089%

    No Known Activations