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

    Neuronpedia

    INDEX
    Explanations

    comparisons between two different things

    oai_token-act-pair · gpt-3.5-turbo

    inquiries about comparisons or proportions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ster
    -0.69
    enburg
    -0.63
    adden
    -0.62
    lich
    -0.60
    por
    -0.60
    eer
    -0.60
     Cong
    -0.59
    jee
    -0.58
    arella
    -0.58
     Sao
    -0.58
    POSITIVE LOGITS
     happens
    1.25
     happened
    1.19
    soever
    1.17
     transpired
    0.99
     happ
    0.96
     constitutes
    0.96
     else
    0.84
     kinds
    0.83
     constituted
    0.79
    Downloadha
    0.75
    Act Density 0.111%

    No Known Activations