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

    Neuronpedia

    INDEX
    Explanations

    terms related to making tasks easier or more convenient

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to convenience or simplicity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ificial
    -0.74
    ertodd
    -0.72
    alion
    -0.71
     Canary
    -0.71
    ortium
    -0.67
    orp
    -0.67
    eters
    -0.67
    ichick
    -0.66
    clusions
    -0.66
    inosaur
    -0.65
    POSITIVE LOGITS
    liness
    0.96
     ease
    0.92
     breeze
    0.75
     easing
    0.73
     familiarity
    0.72
    lihood
    0.71
    joy
    0.70
     relief
    0.69
     Pradesh
    0.69
    ï¸
    0.68
    Act Density 0.025%

    No Known Activations