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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performing actions on specific items in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the concept of singularity or individuality in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     laun
    -0.67
    QL
    -0.66
     oils
    -0.66
     Palestin
    -0.63
     highs
    -0.62
     contrace
    -0.61
    ynt
    -0.60
     transcripts
    -0.60
    Parts
    -0.60
     Clo
    -0.59
    POSITIVE LOGITS
    teenth
    0.92
    ousand
    0.92
    undred
    0.73
    acre
    0.72
    iece
    0.72
    ledged
    0.72
    eenth
    0.71
    fifth
    0.70
    essee
    0.70
    blank
    0.69
    Act Density 0.199%

    No Known Activations