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

    Neuronpedia

    INDEX
    Explanations

    terms related to memory and remembrance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atatype
    -0.16
    ereotype
    -0.15
    sta
    -0.15
    yb
    -0.14
    ãĥ¼ãĥĢ
    -0.14
    adera
    -0.14
    imate
    -0.14
    fos
    -0.14
    erot
    -0.14
     Harness
    -0.14
    POSITIVE LOGITS
    297
    0.17
    ble
    0.17
    ably
    0.16
    uels
    0.16
     Stretch
    0.15
    ju
    0.15
    ously
    0.15
    zÅij
    0.15
    rence
    0.15
    joy
    0.14
    Act Density 0.064%

    No Known Activations