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

    Neuronpedia

    INDEX
    Explanations

    significant phrases or marks indicating a change or a conclusion typically represented by punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.15
    cj
    -0.14
    _DIAG
    -0.14
    alia
    -0.14
    tone
    -0.14
    veh
    -0.14
    .ImageTransparentColor
    -0.14
    Meteor
    -0.14
    uta
    -0.14
    uku
    -0.14
    POSITIVE LOGITS
    illage
    0.18
    ubo
    0.16
    ubs
    0.15
    opers
    0.15
     Grill
    0.14
     lev
    0.14
    ¬
    0.14
     γαÏģ
    0.14
     erect
    0.14
    zzo
    0.14
    Act Density 0.000%

    No Known Activations