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

    Neuronpedia

    INDEX
    Explanations

    references to entities or groups of people engaging in actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SqlCommand
    -0.59
     magát
    -0.57
    󠁢
    -0.54
    rungsseite
    -0.52
     }}"></
    -0.50
    jude
    -0.49
     setInterval
    -0.49
    üğ
    -0.48
    RUnlock
    -0.47
    pins
    -0.47
    POSITIVE LOGITS
     themselves
    2.20
    themselves
    1.88
    Their
    1.87
     Their
    1.75
     their
    1.70
    their
    1.59
     THEIR
    1.51
     thier
    1.20
     deres
    1.17
     leurs
    1.16
    Act Density 0.424%

    No Known Activations