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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of observation or visibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     knowledge
    -0.63
    Ĥİ
    -0.62
    ufact
    -0.61
     ceremon
    -0.59
    inqu
    -0.58
     ACTIONS
    -0.57
     STE
    -0.57
    inion
    -0.56
    Own
    -0.56
    ©¶æ¥µ
    -0.56
    POSITIVE LOGITS
     VIDEOS
    0.95
     similarities
    0.83
     therapist
    0.80
     resemblance
    0.80
     psychiatrist
    0.79
     firsthand
    0.77
     unfold
    0.77
    markets
    0.76
     signs
    0.76
     sunrise
    0.74
    Act Density 0.727%

    No Known Activations