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

    Neuronpedia

    INDEX
    Explanations

    verbs related to observing or noticing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "seeing" or its variations indicating visibility or awareness of occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TO
    -0.74
    ãĥĦ
    -0.71
    eware
    -0.68
    anium
    -0.67
    be
    -0.66
    TL
    -0.64
    toe
    -0.63
    ovie
    -0.63
    cé
    -0.63
    bes
    -0.63
    POSITIVE LOGITS
     firsthand
    1.03
     examples
    0.92
     parallels
    0.88
     similarities
    0.85
     signs
    0.84
     glimps
    0.81
     plenty
    0.81
     visions
    0.79
     hints
    0.78
     alot
    0.77
    Act Density 0.100%

    No Known Activations