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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional expressions and struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocale
    -0.16
     Ans
    -0.16
    YY
    -0.15
    Ans
    -0.15
    zzle
    -0.15
    .vm
    -0.15
    illez
    -0.15
     Grim
    -0.15
     Hum
    -0.15
     Sor
    -0.15
    POSITIVE LOGITS
    dorf
    0.16
     infect
    0.14
     spl
    0.14
    ingham
    0.14
     drawers
    0.13
     aisle
    0.13
    ÑĢави
    0.13
    åħ±
    0.13
     thrust
    0.13
    alter
    0.13
    Act Density 0.154%

    No Known Activations