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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement back and forth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÌĨ
    -0.16
    prov
    -0.16
    ĥĿ
    -0.15
    adiens
    -0.14
    edis
    -0.14
    ürn
    -0.14
    reas
    -0.14
    acy
    -0.13
     AVL
    -0.13
     Mell
    -0.13
    POSITIVE LOGITS
    sar
    0.17
    änge
    0.14
    cul
    0.14
    dek
    0.14
    .toolbox
    0.14
    alar
    0.14
    oundation
    0.14
    umble
    0.14
    .cwd
    0.13
    ForObject
    0.13
    Act Density 0.011%

    No Known Activations