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

    Neuronpedia

    INDEX
    Explanations

    phrases related to observation or witnessing significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nacht
    -0.16
    iffe
    -0.16
    aeda
    -0.15
    hoo
    -0.15
     Balls
    -0.14
    uforia
    -0.14
    quot
    -0.14
    foon
    -0.14
    ìĥĪ
    -0.14
    éri
    -0.14
    POSITIVE LOGITS
    neh
    0.16
    icom
    0.15
    åĬ¨
    0.15
     Norman
    0.15
    iš
    0.15
    hlen
    0.14
    ạ
    0.14
     dynamic
    0.14
    æĵ
    0.14
     process
    0.14
    Act Density 0.302%

    No Known Activations