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

    Neuronpedia

    INDEX
    Explanations

    statements indicating existence or descriptions of conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    this
    -0.15
    soever
    -0.14
    vis
    -0.14
    uba
    -0.14
    379
    -0.14
    opause
    -0.14
     there
    -0.14
    port
    -0.14
    there
    -0.14
    763
    -0.13
    POSITIVE LOGITS
     how
    0.23
     where
    0.21
     why
    0.21
     happening
    0.19
    how
    0.16
    AFX
    0.16
    aran
    0.15
    why
    0.15
     happ
    0.15
     supposed
    0.15
    Act Density 0.108%

    No Known Activations