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

    Neuronpedia

    INDEX
    Explanations

    expressions of visual assessment or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    looks like an observation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adhyay
    -0.53
    ragamo
    -0.51
    ibrate
    -0.51
     Nantucket
    -0.50
    ghum
    -0.49
    passphrase
    -0.49
     Vineyard
    -0.48
     tričko
    -0.47
    ppuden
    -0.47
     hostage
    -0.47
    POSITIVE LOGITS
    Looks
    1.45
     Looks
    1.41
    looks
    1.31
     looks
    1.31
     LOOKS
    1.22
    seems
    0.77
    appears
    0.71
     aussieht
    0.70
     seems
    0.69
    Parece
    0.69
    Act Density 0.004%

    No Known Activations