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

    Neuronpedia

    INDEX
    Explanations

    affirmative phrases related to the evolution of technology and its impact on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umpt
    -0.15
    ëŀµ
    -0.15
    amt
    -0.14
     @{$
    -0.14
     initi
    -0.14
     reverted
    -0.13
    ladu
    -0.13
    ooke
    -0.13
    izr
    -0.13
    agma
    -0.13
    POSITIVE LOGITS
     gain
    0.39
     gained
    0.37
     gaining
    0.35
     gains
    0.31
     Gain
    0.31
    gain
    0.29
    Gain
    0.29
     spread
    0.29
     popularity
    0.28
    bec
    0.27
    Act Density 0.206%

    No Known Activations