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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating levels or degrees of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -0.72
    i
    -0.63
    The
    -0.57
     pagrind
    -0.56
    the
    -0.55
     iscri
    -0.54
    u
    -0.53
     démission
    -0.53
     menikah
    -0.52
    l
    -0.52
    POSITIVE LOGITS
    `,
    1.07
    HasAnnotation
    1.06
    ]--;
    1.01
     BoxFit
    1.01
    UIControlState
    1.00
    "):
    1.00
     GenerationType
    0.99
     snippetHide
    0.99
    )++;
    0.97
    ]='\
    0.96
    Act Density 0.547%

    No Known Activations