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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional possibilities or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    бÑĥд
    -0.16
    èĽĽ
    -0.16
    çĦ¶
    -0.16
    ngle
    -0.16
    arf
    -0.15
    brick
    -0.15
    ekten
    -0.14
    lod
    -0.14
    ari
    -0.14
     Jacqu
    -0.14
    POSITIVE LOGITS
    ul
    0.16
    ’ve
    0.15
    ulp
    0.15
     kdyby
    0.14
    've
    0.14
     wouldn
    0.14
    Ń
    0.14
    nt
    0.14
    æŃ
    0.14
     åģ
    0.13
    Act Density 0.693%

    No Known Activations