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

    Neuronpedia

    INDEX
    Explanations

    words related to naming or naming conventions, often related to human names or geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to etymology or origins of names and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fficiency
    -0.70
    ensibly
    -0.69
    inarily
    -0.68
    displayText
    -0.67
    ahead
    -0.67
    amina
    -0.67
    dule
    -0.66
    cipled
    -0.66
    Ops
    -0.65
    erity
    -0.65
    POSITIVE LOGITS
     poem
    0.89
     motto
    0.83
    /
    0.78
     slogan
    0.77
     philosophies
    0.77
     cartoons
    0.76
     folklore
    0.74
     proverb
    0.74
     playbook
    0.74
     famous
    0.74
    Act Density 0.659%

    No Known Activations