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

    Neuronpedia

    INDEX
    Explanations

    assertive or declarative statements that highlight opinions or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     imb
    -0.44
     believed
    -0.44
    InitVars
    -0.43
    ="&#
    -0.43
     Belie
    -0.42
    HasIndex
    -0.42
     claimed
    -0.41
     ul
    -0.41
    ButterKnife
    -0.40
     Felt
    -0.40
    POSITIVE LOGITS
     surla
    0.54
    RTLI
    0.46
    InputTagHelper
    0.43
     apó
    0.42
    tangentMode
    0.41
    aptation
    0.41
    enumii
    0.41
     mourut
    0.41
    enumi
    0.40
     ſtand
    0.40
    Act Density 0.160%

    No Known Activations