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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey a basis or reasoning for claims or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tempt
    -0.14
    erson
    -0.14
    ìĪ
    -0.14
    oq
    -0.14
    olah
    -0.14
    oplevel
    -0.14
    rella
    -0.14
    ç¹Ķ
    -0.13
    pole
    -0.13
    ike
    -0.13
    POSITIVE LOGITS
     principle
    0.14
    licer
    0.14
     principles
    0.14
    664
    0.14
    veyor
    0.13
    ylon
    0.13
    _interfaces
    0.13
    -metadata
    0.13
    ymous
    0.13
    olen
    0.13
    Act Density 0.056%

    No Known Activations