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

    Neuronpedia

    INDEX
    Explanations

    occurrences of file paths or directory references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imbus
    -0.14
    inking
    -0.14
    Destroyed
    -0.14
    umerator
    -0.14
    ủi
    -0.13
    enment
    -0.13
    ceae
    -0.13
    Sec
    -0.13
    νε
    -0.13
    ampions
    -0.13
    POSITIVE LOGITS
    adoo
    0.27
    base
    0.24
    Base
    0.24
    adoop
    0.21
    iera
    0.21
    ado
    0.21
    ive
    0.21
    IVE
    0.20
    BASE
    0.19
    ADO
    0.19
    Act Density 0.013%

    No Known Activations