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

    Neuronpedia

    INDEX
    Explanations

    entities and names associated with cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etas
    -0.15
    cala
    -0.15
    zahl
    -0.15
    ummer
    -0.14
    zag
    -0.14
    aces
    -0.14
    ties
    -0.14
    jr
    -0.14
    ONS
    -0.14
    igner
    -0.14
    POSITIVE LOGITS
     Ts
    0.29
    unami
    0.28
     ts
    0.26
    /ts
    0.22
    (ts
    0.21
    Ts
    0.21
    avorite
    0.21
    .ts
    0.20
     TS
    0.20
    utom
    0.20
    Act Density 0.008%

    No Known Activations