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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical errors or issues with subscribing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to waiting or delays in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owship
    -0.81
    ³³³³³³³³³³³³³³³³
    -0.81
    roots
    -0.74
    pit
    -0.73
    ³³³³³³³³
    -0.72
     Shack
    -0.69
    Extreme
    -0.69
    oft
    -0.68
    dust
    -0.66
    bah
    -0.66
    POSITIVE LOGITS
     delete
    0.84
     skip
    0.68
     verify
    0.68
    iator
    0.68
     login
    0.66
     overwrite
    0.65
     update
    0.65
     than
    0.65
    uters
    0.64
     unlocks
    0.64
    Act Density 0.014%

    No Known Activations