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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or entities being the best or most notable in their field or category

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erto
    -0.82
    insula
    -0.71
     fixme
    -0.66
     ensu
    -0.63
     pitch
    -0.62
    ramid
    -0.62
    ertodd
    -0.62
    ailability
    -0.62
     heels
    -0.61
    uckland
    -0.60
    POSITIVE LOGITS
    frames
    1.02
    glass
    0.91
    flies
    0.88
    frame
    0.82
    cia
    0.81
     ago
    0.81
    geist
    0.80
    bender
    0.79
    bell
    0.75
     Spiral
    0.75
    Act Density 0.071%

    No Known Activations