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

    Neuronpedia

    INDEX
    Explanations

    terms related to large-scale impactful events or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'huge' or its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.77
    printed
    -0.69
     Hemp
    -0.68
    netflix
    -0.68
     unbeat
    -0.63
    iph
    -0.62
    organic
    -0.61
    orescent
    -0.61
     overheard
    -0.60
    icum
    -0.60
    POSITIVE LOGITS
    uge
    1.34
    glers
    0.90
    UGE
    0.90
    uese
    0.83
    gery
    0.77
    llo
    0.76
    aten
    0.76
    rers
    0.76
    ãĥ¼ãĥĨãĤ£
    0.74
    ction
    0.74
    Act Density 0.002%

    No Known Activations