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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating unintended consequences or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inkel
    -0.16
     Sesso
    -0.15
    icas
    -0.15
    gren
    -0.14
     Slate
    -0.14
    atta
    -0.14
     passive
    -0.14
    DataContract
    -0.14
    å§ij
    -0.14
    itas
    -0.13
    POSITIVE LOGITS
    çĦ
    0.18
    sap
    0.17
    archical
    0.17
     Broken
    0.15
    hti
    0.15
    ystack
    0.15
    777
    0.14
     Ø´Ùħ
    0.14
    739
    0.14
    Truthy
    0.14
    Act Density 0.005%

    No Known Activations