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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user interaction and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ý
    -0.17
    ôm
    -0.15
     ΣÏį
    -0.15
    exus
    -0.15
     поÑĢÑıдкÑĥ
    -0.14
    ëģĶ
    -0.14
    ÑģÑĤи
    -0.14
    avel
    -0.14
    /=
    -0.14
    nth
    -0.14
    POSITIVE LOGITS
    uet
    0.15
    çª
    0.14
    aze
    0.14
    araoh
    0.14
    ase
    0.14
     mc
    0.14
     Zap
    0.14
     inter
    0.14
    害
    0.14
    AZE
    0.13
    Act Density 0.136%

    No Known Activations