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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating statements or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    states that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jody
    -0.57
    errHandler
    -0.57
     microm
    -0.56
    mixins
    -0.54
    bardier
    -0.53
     Oberlin
    -0.52
    harness
    -0.51
     ubi
    -0.51
    ByVersion
    -0.51
    pilot
    -0.51
    POSITIVE LOGITS
     stated
    1.05
     stating
    1.00
     statement
    0.79
     statements
    0.74
     stwier
    0.69
     déclare
    0.69
     Statement
    0.66
     ilmo
    0.66
     states
    0.66
     afirmou
    0.64
    Act Density 0.024%

    No Known Activations