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

    Neuronpedia

    INDEX
    Explanations

    expressions related to opportunities for learning and cultural experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agram
    -0.17
     ëĦ¤ìĿ´íĬ¸
    -0.16
    strand
    -0.15
    ÑıÑģÑĮ
    -0.14
    JKLM
    -0.14
    achie
    -0.14
    agrams
    -0.13
    Reached
    -0.13
     اÙĦÙħدر
    -0.13
    abee
    -0.13
    POSITIVE LOGITS
     experience
    0.34
     gain
    0.34
     learn
    0.33
     imm
    0.32
     exposure
    0.30
     gaining
    0.30
     Gain
    0.30
    Gain
    0.30
    learn
    0.28
     learns
    0.28
    Act Density 0.226%

    No Known Activations