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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their associated verbs to understand personal narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umm
    -0.17
    _IOC
    -0.15
    .Tables
    -0.14
    ály
    -0.14
    ÙĨÙĬÙĨ
    -0.14
     Alarm
    -0.14
    amen
    -0.13
    ahir
    -0.13
    ube
    -0.13
    Alarm
    -0.13
    POSITIVE LOGITS
    /or
    0.21
     vic
    0.16
     pant
    0.14
    uky
    0.14
    arine
    0.14
    åħį
    0.13
    hetto
    0.13
    rog
    0.13
    -overlay
    0.13
     thus
    0.13
    Act Density 0.207%

    No Known Activations