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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong feelings or significant experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucci
    -0.16
    qid
    -0.16
     Alman
    -0.15
    895
    -0.15
    isku
    -0.14
    orsch
    -0.14
    maj
    -0.13
    263
    -0.13
    mam
    -0.13
    ordes
    -0.13
    POSITIVE LOGITS
    agle
    0.14
    uste
    0.14
    imd
    0.14
    embed
    0.14
     alright
    0.14
    Specification
    0.13
     ëĨ
    0.13
    -tabs
    0.13
    etail
    0.13
    eras
    0.13
    Act Density 0.140%

    No Known Activations