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

    Neuronpedia

    INDEX
    Explanations

    things described as unique or distinctive in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     piger
    -0.16
    anten
    -0.15
     èĩªåĬ¨çĶŁæĪIJ
    -0.15
    ilha
    -0.15
    lick
    -0.14
    lish
    -0.14
    ierce
    -0.14
    agua
    -0.14
     lamin
    -0.14
    ldr
    -0.14
    POSITIVE LOGITS
    amera
    0.14
    hey
    0.14
    ivo
    0.14
    Msp
    0.14
    eydi
    0.14
    textInput
    0.13
    æķ¢
    0.13
    KER
    0.13
    HEY
    0.13
    emann
    0.13
    Act Density 0.013%

    No Known Activations