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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the purpose or aim of a project, study, or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe the objectives or aims of projects and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashtra
    -0.79
    edge
    -0.67
    resistant
    -0.67
    issues
    -0.66
    grain
    -0.65
    thur
    -0.64
     Leopard
    -0.64
     trem
    -0.63
    orce
    -0.62
     ILCS
    -0.62
    POSITIVE LOGITS
     maximizing
    0.77
     supplying
    0.71
     recruitment
    0.71
     preserving
    0.70
     promoting
    0.69
    thood
    0.69
     constructing
    0.69
     obtaining
    0.68
     endeavor
    0.68
     neutrality
    0.68
    Act Density 0.133%

    No Known Activations