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

    Neuronpedia

    INDEX
    Explanations

    references to concepts of existence and presence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inSlope
    -0.40
    Autoritní
    -0.39
    __":
    -0.36
    ronpa
    -0.36
    nologue
    -0.35
    までに
    -0.34
    SuccessListener
    -0.33
    󠁧
    -0.31
    눠
    -0.31
     ligiloj
    -0.31
    POSITIVE LOGITS
     always
    4.28
    always
    3.83
     Always
    3.59
    Always
    3.59
     siempre
    3.53
     sempre
    3.50
     zawsze
    3.27
     всегда
    3.22
     ALWAYS
    3.13
    siempre
    3.08
    Act Density 1.417%

    No Known Activations