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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'first' occurring in sentences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "first."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.76
    mbuds
    -0.74
    acons
    -0.71
    Progress
    -0.70
    borg
    -0.69
    pers
    -0.68
    athed
    -0.66
    leaders
    -0.66
    apped
    -0.64
    STEM
    -0.63
    POSITIVE LOGITS
     thing
    1.02
     iteration
    0.95
     few
    0.93
     batch
    0.93
     couple
    0.92
     installment
    0.91
     baseman
    0.91
     step
    0.90
     layer
    0.90
     glance
    0.90
    Act Density 0.128%

    No Known Activations