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

    Neuronpedia

    INDEX
    Explanations

    references to historical events or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olo
    -0.18
    reo
    -0.17
    elo
    -0.17
    oj
    -0.16
    sson
    -0.16
    ppo
    -0.16
    ers
    -0.16
    eso
    -0.15
    ember
    -0.15
    ines
    -0.14
    POSITIVE LOGITS
    TOTYPE
    0.17
    rosso
    0.15
    criptor
    0.15
    argout
    0.15
    UNET
    0.14
    ivos
    0.14
     luder
    0.14
    piring
    0.14
    .INSTANCE
    0.14
    ãİ¡
    0.14
    Act Density 0.011%

    No Known Activations