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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating experience or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idges
    -0.16
    onces
    -0.15
    adge
    -0.14
    annis
    -0.14
     ages
    -0.14
    948
    -0.14
    utan
    -0.14
    649
    -0.14
    contres
    -0.14
    olean
    -0.14
    POSITIVE LOGITS
    oda
    0.15
     scal
    0.15
    pNext
    0.14
    acro
    0.14
    .sdk
    0.14
    à¥Īल
    0.14
    алÑİ
    0.13
    alleries
    0.13
    jit
    0.13
    åde
    0.13
    Act Density 0.044%

    No Known Activations