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

    Neuronpedia

    INDEX
    Explanations

    terms related to rejection and warranties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cir
    -0.43
     Grand
    -0.39
     referrerpolicy
    -0.37
    <bos>
    -0.33
     jam
    -0.32
     IF
    -0.32
     Mor
    -0.32
    getInteger
    -0.32
     min
    -0.32
     Ju
    -0.31
    POSITIVE LOGITS
     ब्रेकडाउन
    0.84
    DrawerToggle
    0.73
    Buck
    0.68
    ſelves
    0.67
    Annex
    0.66
     canst
    0.65
     Reject
    0.65
    ſelf
    0.65
     Reſ
    0.64
    ſhip
    0.64
    Act Density 0.305%

    No Known Activations