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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to things taken for granted

    oai_token-act-pair · gpt-3.5-turbo

    references to taking things for granted

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arnaev
    -0.78
    asus
    -0.74
    visor
    -0.71
    pi
    -0.71
    sis
    -0.71
    gins
    -0.70
    center
    -0.69
    byn
    -0.68
    rigan
    -0.68
    adra
    -0.68
    POSITIVE LOGITS
     anymore
    0.81
     athlet
    0.72
     nowadays
    0.66
     uncond
    0.65
     nostalg
    0.61
     deadlines
    0.61
    enance
    0.61
     outlet
    0.60
     stares
    0.59
     Pwr
    0.59
    Act Density 0.014%

    No Known Activations