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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "in" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Whig
    -0.71
    ᅠ
    -0.70
     linseed
    -0.68
     Mako
    -0.68
     leão
    -0.66
     negroes
    -0.65
     thermomix
    -0.65
     Abonnez
    -0.64
     تضيفلها
    -0.63
     papy
    -0.63
    POSITIVE LOGITS
     the
    1.04
     a
    0.90
     an
    0.72
     different
    0.71
     Lid
    0.59
    ocities
    0.59
     them
    0.59
    MemoryWarning
    0.59
     another
    0.59
    orse
    0.57
    Act Density 0.050%

    No Known Activations