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

    Neuronpedia

    INDEX
    Explanations

    sentences that express strong opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -0.60
     Efq
    -0.59
     jsPsych
    -0.56
    ViewFeatures
    -0.55
    skjaer
    -0.54
    Przeczytaj
    -0.53
    ...");
    -0.52
    יבה
    -0.51
     ...
    -0.50
    SupportActionBar
    -0.50
    POSITIVE LOGITS
     therefore
    0.59
     not
    0.57
    SpringBootTest
    0.56
     Therefore
    0.55
     endwhile
    0.52
    Therefore
    0.52
     so
    0.50
    yal
    0.49
    ’
    0.48
     abrazo
    0.47
    Act Density 0.308%

    No Known Activations