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

    Neuronpedia

    INDEX
    Explanations

    technical terms and references related to various scientific fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,:);
    -0.70
     itſelf
    -0.70
    iciary
    -0.69
     Obrador
    -0.68
    ]='\
    -0.67
    akterysty
    -0.66
    ,:)
    -0.66
    thâu
    -0.65
    }")
    -0.65
    Ufficio
    -0.65
    POSITIVE LOGITS
    um
    0.50
     sar
    0.48
    isi
    0.48
    Tenure
    0.48
    Um
    0.47
    Emp
    0.47
     innings
    0.47
     Um
    0.47
    EndContext
    0.46
     PLEAS
    0.44
    Act Density 2.910%

    No Known Activations