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

    Neuronpedia

    INDEX
    Explanations

    references to meetings and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é»
    -0.16
    osaur
    -0.15
    å¤ķ
    -0.14
    chestra
    -0.14
    ilha
    -0.14
    efined
    -0.14
    reso
    -0.14
    spender
    -0.13
    eos
    -0.13
    ovie
    -0.13
    POSITIVE LOGITS
    igo
    0.17
    nonce
    0.16
    lop
    0.16
     riêng
    0.15
    ictory
    0.15
    IGO
    0.14
    loff
    0.14
    laus
    0.14
     Sala
    0.14
    enne
    0.14
    Act Density 0.257%

    No Known Activations