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

    Neuronpedia

    INDEX
    Explanations

    pronouns and spatial references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lify
    -0.16
    alars
    -0.15
    arently
    -0.15
     "***
    -0.14
    nÃŃ
    -0.14
     Antar
    -0.13
    .EventQueue
    -0.13
    tainment
    -0.13
    arem
    -0.13
    бом
    -0.13
    POSITIVE LOGITS
     Spoon
    0.15
    Ìī
    0.14
    pline
    0.14
    vier
    0.14
    ãģ£ãģı
    0.13
    gba
    0.13
    908
    0.13
    ivec
    0.13
    licos
    0.13
     Brennan
    0.12
    Act Density 1.502%

    No Known Activations