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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "become" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uan
    -0.17
     ActionTypes
    -0.16
    tele
    -0.15
     Jako
    -0.14
     αξ
    -0.14
    umb
    -0.14
    izzato
    -0.14
    achable
    -0.14
    196
    -0.14
    AES
    -0.13
    POSITIVE LOGITS
    icode
    0.16
    lán
    0.15
    etus
    0.14
    chu
    0.14
    OURCES
    0.14
    sb
    0.14
    anggan
    0.14
    suffix
    0.13
    Poly
    0.13
    _direct
    0.13
    Act Density 0.029%

    No Known Activations