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

    Neuronpedia

    INDEX
    Explanations

    words related to programs or organized activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various programs or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jr
    -0.72
    hiro
    -0.72
    pg
    -0.66
     stake
    -0.64
    vg
    -0.62
    vae
    -0.61
    ulf
    -0.61
    yll
    -0.61
    ournaments
    -0.61
    lake
    -0.61
    POSITIVE LOGITS
    mable
    1.20
     programme
    1.13
     programmes
    1.10
     Programme
    1.03
    matic
    1.01
    matically
    0.96
    eers
    0.82
    ĸļ
    0.78
    mers
    0.74
    caster
    0.74
    Act Density 0.020%

    No Known Activations