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

    Neuronpedia

    INDEX
    Explanations

    words related to solid substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various classes of biological organisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Employment
    -0.66
     contradiction
    -0.65
     pardon
    -0.60
     questioning
    -0.60
     comfort
    -0.59
     competence
    -0.59
     mach
    -0.59
     hesitation
    -0.58
     labour
    -0.56
     labor
    -0.56
    POSITIVE LOGITS
    ids
    4.60
    IDS
    2.16
    IDs
    2.07
    id
    2.04
    ID
    1.61
    idding
    1.60
    idd
    1.59
    idae
    1.44
    ides
    1.43
    idity
    1.42
    Act Density 0.017%

    No Known Activations