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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future intentions or desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.15
    hiro
    -0.15
    resi
    -0.14
    oulouse
    -0.14
    fork
    -0.14
    esar
    -0.14
    ufe
    -0.14
     Hayes
    -0.14
    omain
    -0.13
    ilen
    -0.13
    POSITIVE LOGITS
    onda
    0.15
    ittel
    0.15
    oir
    0.14
     beh
    0.14
    itable
    0.14
    omu
    0.14
    OnClick
    0.14
    steder
    0.14
    loc
    0.14
    achi
    0.14
    Act Density 0.012%

    No Known Activations