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

    Neuronpedia

    INDEX
    Explanations

    instances of object references in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chad
    -0.68
    ing
    -0.67
     Ake
    -0.66
     }^{(
    -0.66
    }^{(
    -0.63
    Appe
    -0.61
     Hatt
    -0.61
    zewod
    -0.60
    Aten
    -0.59
    </h2>
    -0.59
    POSITIVE LOGITS
    objectives
    1.07
    mployed
    1.01
    ceutical
    1.01
    obj
    1.00
     obj
    0.97
    ilions
    0.96
    ISY
    0.96
    selves
    0.96
     Obj
    0.92
    otry
    0.90
    Act Density 0.145%

    No Known Activations