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

    Neuronpedia

    INDEX
    Explanations

    exclamations and positive affirmations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positivity or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaz
    -0.73
     guiActiveUn
    -0.69
    ascus
    -0.68
    ural
    -0.67
    urities
    -0.65
    IRE
    -0.65
    gypt
    -0.65
    uterte
    -0.65
    rose
    -0.65
    inez
    -0.64
    POSITIVE LOGITS
     albeit
    0.94
    albeit
    0.81
     congratulations
    0.79
     huh
    0.75
    enough
    0.71
     insofar
    0.69
     but
    0.69
     Especially
    0.69
     BUT
    0.69
    âĹ¼
    0.67
    Act Density 0.556%

    No Known Activations