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

    Neuronpedia

    INDEX
    Explanations

    complex or contrasting phrases

    oai_token-act-pair · gpt-3.5-turbo

    contrastive conjunctions and qualifiers that indicate complexity or nuance in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mpeg
    -0.86
    ouses
    -0.78
    oku
    -0.77
    anners
    -0.75
     //[
    -0.72
    okemon
    -0.72
    ramids
    -0.72
    bos
    -0.71
    atari
    -0.68
    kees
    -0.68
    POSITIVE LOGITS
     unden
    0.95
     unintentional
    0.82
     economical
    0.81
     effic
    0.79
     unsur
    0.78
     consequential
    0.77
     unbiased
    0.76
     unpop
    0.76
     profitable
    0.76
     uncom
    0.75
    Act Density 0.220%

    No Known Activations