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

    Neuronpedia

    INDEX
    Explanations

    repetitive patterns or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize repetition or recurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTS
    -0.83
    asty
    -0.76
    tein
    -0.72
    gewater
    -0.71
    gio
    -0.71
    uador
    -0.70
    iso
    -0.68
    isting
    -0.68
    ghai
    -0.68
    /#
    -0.68
    POSITIVE LOGITS
    theless
    0.84
     throughout
    0.83
    entimes
    0.76
     cycles
    0.72
    ciating
    0.69
     assail
    0.69
     recite
    0.68
     thereafter
    0.68
     msec
    0.67
     alike
    0.66
    Act Density 0.025%

    No Known Activations