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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases emphasizing similarity or equivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -0.17
    ulus
    -0.16
    egra
    -0.15
    owo
    -0.14
    oples
    -0.14
    orre
    -0.14
    tte
    -0.14
     initials
    -0.14
     Very
    -0.14
    æĽ´
    -0.13
    POSITIVE LOGITS
     much
    0.26
     close
    0.21
    close
    0.21
     likely
    0.21
    inine
    0.20
    warm
    0.19
    cert
    0.19
    phy
    0.18
    much
    0.18
    Much
    0.18
    Act Density 0.035%

    No Known Activations