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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¹
    -0.15
    ovich
    -0.15
    alo
    -0.14
    rik
    -0.14
    476
    -0.14
    rick
    -0.14
    nt
    -0.13
    alers
    -0.13
    rape
    -0.13
    íĦ¸
    -0.13
    POSITIVE LOGITS
     match
    0.28
     longer
    0.23
    xious
    0.23
    -match
    0.22
     Buen
    0.21
    match
    0.21
     different
    0.20
     Match
    0.20
     substitute
    0.19
    Match
    0.19
    Act Density 0.020%

    No Known Activations