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

    Neuronpedia

    INDEX
    Explanations

    concepts related to rules and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rello
    -0.15
    ;base
    -0.15
    rait
    -0.15
    batim
    -0.14
    Ðĩ
    -0.14
    orgot
    -0.14
    iÄįe
    -0.14
    iox
    -0.14
    UBY
    -0.14
     Mandatory
    -0.13
    POSITIVE LOGITS
     safe
    0.40
     safety
    0.36
     safely
    0.35
    safe
    0.35
     Safe
    0.34
     protected
    0.33
    -safe
    0.33
     safest
    0.32
    Safe
    0.31
    å®īåħ¨
    0.31
    Act Density 0.109%

    No Known Activations