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

    Neuronpedia

    INDEX
    Explanations

    phrases and structures indicating actions related to assistance and sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apikey
    -0.53
     doigt
    -0.52
     Kr
    -0.51
    的一种
    -0.49
    SPIRE
    -0.48
    MBOL
    -0.48
    eree
    -0.48
     hinaus
    -0.47
    hamcrest
    -0.47
    WithError
    -0.47
    POSITIVE LOGITS
    ########.
    0.81
     متعلقه
    0.65
    Autoritní
    0.64
     فريبيس
    0.62
     Signalez
    0.56
     every
    0.56
     мәкал
    0.52
    every
    0.52
    GeneratedCode
    0.51
    Према
    0.51
    Act Density 0.308%

    No Known Activations