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

    Neuronpedia

    INDEX
    Explanations

    words related to growth or increase

    oai_token-act-pair · gpt-3.5-turbo

    terms related to growth or increased intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©
    -0.76
    phis
    -0.74
     Rouge
    -0.68
    stice
    -0.67
    orneys
    -0.66
    hra
    -0.66
    odan
    -0.64
    oute
    -0.64
    ioned
    -0.64
     Mub
    -0.63
    POSITIVE LOGITS
     exponentially
    1.05
     pains
    0.94
     promot
    0.89
     explos
    0.81
     accustomed
    0.80
     enormously
    0.78
     stronger
    0.76
     tremendously
    0.75
     immensely
    0.75
     closer
    0.72
    Act Density 0.046%

    No Known Activations