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

    Neuronpedia

    INDEX
    Explanations

    words related to a large quantity or sudden increase of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to large quantities or significant movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.83
     scales
    -0.68
    BIT
    -0.67
    verbs
    -0.63
     accur
    -0.61
     principles
    -0.60
     shortcuts
    -0.60
     MFT
    -0.58
    VICE
    -0.56
     grids
    -0.56
    POSITIVE LOGITS
     of
    0.95
    pour
    0.93
    lust
    0.78
    stakes
    0.76
    luster
    0.74
     thereof
    0.74
     OF
    0.73
    oning
    0.73
    govtrack
    0.72
     Of
    0.70
    Act Density 0.119%

    No Known Activations