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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cleaning or organizing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    place
    -0.19
    esters
    -0.17
    reira
    -0.16
    presso
    -0.15
    quette
    -0.15
    odore
    -0.15
    ük
    -0.14
    eger
    -0.14
    ÑĢ
    -0.14
    orio
    -0.14
    POSITIVE LOGITS
    datable
    0.26
    /down
    0.23
    dater
    0.21
    shot
    0.21
    sk
    0.20
    turned
    0.19
    ture
    0.18
    pers
    0.18
    ped
    0.17
    ping
    0.17
    Act Density 0.134%

    No Known Activations