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

    Neuronpedia

    INDEX
    Explanations

    discrepancies between stated intentions and actual outcomes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isks
    -0.19
    ;element
    -0.17
    ibbon
    -0.16
    esini
    -0.16
    essim
    -0.16
     поба
    -0.16
    otton
    -0.15
    isque
    -0.15
    ottom
    -0.15
    HeaderCode
    -0.14
    POSITIVE LOGITS
     reality
    0.26
     Reality
    0.20
    Reality
    0.19
     realities
    0.18
     Bur
    0.17
    121
    0.16
    216
    0.15
     cheap
    0.14
    ety
    0.14
     realidad
    0.14
    Act Density 0.145%

    No Known Activations