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

    Neuronpedia

    INDEX
    Explanations

    dialogue and expressions of desire or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    're
    -0.18
    лаÑģ
    -0.17
    ’re
    -0.16
    abeth
    -0.15
    currently
    -0.14
    zzo
    -0.14
    ding
    -0.14
    nid
    -0.14
    ambda
    -0.14
    uckles
    -0.14
    POSITIVE LOGITS
     shall
    0.25
     fancy
    0.22
    shall
    0.21
     appreh
    0.20
    ancy
    0.19
     protest
    0.19
     sha
    0.19
     SHALL
    0.18
     repeat
    0.17
     venture
    0.17
    Act Density 0.124%

    No Known Activations