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

    Neuronpedia

    INDEX
    Explanations

    sentences describing observation, evaluation, or realization

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating perception or observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufact
    -0.96
    angan
    -0.74
     depended
    -0.69
    lette
    -0.64
     Huntington
    -0.63
    aga
    -0.62
    ulo
    -0.62
     STE
    -0.59
    }{
    -0.59
    atton
    -0.59
    POSITIVE LOGITS
     VIDEOS
    0.91
     firsthand
    0.85
     unfold
    0.83
    ideos
    0.75
     videos
    0.72
    markets
    0.71
     therapist
    0.70
     positives
    0.66
     resemblance
    0.65
    deen
    0.64
    Act Density 0.248%

    No Known Activations