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

    Neuronpedia

    INDEX
    Explanations

    colorful descriptors or items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to repayment and colorful descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urg
    -0.89
    ulhu
    -0.82
    orb
    -0.81
    ologist
    -0.80
    ologic
    -0.80
    otropic
    -0.77
    alez
    -0.77
    ologically
    -0.77
    ologists
    -0.76
    imer
    -0.76
    POSITIVE LOGITS
    lihood
    1.00
    theless
    0.81
    thood
    0.77
     embell
    0.70
    backer
    0.68
    tons
    0.67
    issance
    0.65
    aces
    0.65
     heck
    0.62
     Kafka
    0.61
    Act Density 0.057%

    No Known Activations