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

    Neuronpedia

    INDEX
    Explanations

    terms related to promotional offers and bonuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.19
    idar
    -0.16
     impulse
    -0.15
    ector
    -0.14
     manner
    -0.14
    899
    -0.14
     spat
    -0.14
    arge
    -0.14
    pNet
    -0.13
    .Utc
    -0.13
    POSITIVE LOGITS
    lef
    0.17
    alara
    0.15
    alars
    0.15
    eto
    0.14
    ele
    0.14
    aler
    0.14
    ourcing
    0.13
     Sof
    0.13
    -basket
    0.13
    rror
    0.13
    Act Density 0.037%

    No Known Activations