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

    Neuronpedia

    INDEX
    Explanations

    phrases related to planning and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /wait
    -0.15
     tant
    -0.13
     Neville
    -0.13
    ãģĵãĤĵãģ«
    -0.13
    äge
    -0.13
     Benedict
    -0.13
    .ravel
    -0.13
    illion
    -0.13
     lor
    -0.13
    éĻµ
    -0.13
    POSITIVE LOGITS
    igan
    0.16
    ноÑĪ
    0.15
    ivan
    0.15
    /by
    0.15
    }.{
    0.14
    анÑģи
    0.14
     cái
    0.14
    adx
    0.14
    andin
    0.14
    PIC
    0.13
    Act Density 0.175%

    No Known Activations