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

    Neuronpedia

    INDEX
    Explanations

    sentences discussing the existence or presence of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the existence or presence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.62
     Armored
    -0.59
     Heights
    -0.59
     cylinders
    -0.56
     Doom
    -0.55
     Throne
    -0.54
     actionGroup
    -0.54
     Injury
    -0.54
     Buck
    -0.52
     Tibet
    -0.52
    POSITIVE LOGITS
    abouts
    1.36
    upon
    1.17
    fore
    0.82
    with
    0.79
    after
    0.77
    FORE
    0.73
    é¾į
    0.72
    wegian
    0.71
     SHALL
    0.71
    ported
    0.70
    Act Density 0.116%

    No Known Activations