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

    Neuronpedia

    INDEX
    Explanations

    phrases related to creating or customizing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of ownership or creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hovah
    -0.81
    anwhile
    -0.80
    lehem
    -0.79
     Mub
    -0.75
    usted
    -0.73
    erest
    -0.72
    olic
    -0.69
    ysical
    -0.67
    akings
    -0.67
    Prev
    -0.67
    POSITIVE LOGITS
     version
    0.91
     custom
    0.86
     customized
    0.84
     personalized
    0.83
     copy
    0.79
     unique
    0.76
     versions
    0.73
     personal
    0.73
     selves
    0.72
     accord
    0.71
    Act Density 0.033%

    No Known Activations