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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different levels or degrees of something

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate varying degrees or levels of intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cyborg
    -0.59
     beaut
    -0.53
     Bullets
    -0.53
     backfield
    -0.52
     Klux
    -0.51
     Doors
    -0.51
     Bars
    -0.50
     Stars
    -0.49
     Trophy
    -0.49
    miah
    -0.49
    POSITIVE LOGITS
     of
    1.02
    atos
    0.83
    of
    0.82
    Of
    0.77
    atical
    0.77
     thereof
    0.75
    pour
    0.71
    fare
    0.70
    ically
    0.69
    ulet
    0.69
    Act Density 0.254%

    No Known Activations