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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a significant or essential change or concept

    oai_token-act-pair · gpt-3.5-turbo

    the word "fundamentally" and variations of it used to emphasize core changes or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ries
    -0.77
    ibal
    -0.65
     Guys
    -0.64
     supervisors
    -0.64
     Commissioners
    -0.64
     Leone
    -0.64
     Slaughter
    -0.64
    icip
    -0.63
    tein
    -0.63
     runners
    -0.60
    POSITIVE LOGITS
     opposed
    0.81
     flawed
    0.80
     differentiated
    0.80
     wedd
    0.80
    ascript
    0.78
     altering
    0.74
     incapable
    0.74
     embodied
    0.72
     reliant
    0.71
    gebra
    0.71
    Act Density 0.021%

    No Known Activations