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

    Neuronpedia

    INDEX
    Explanations

    instances or phrases indicating a change in status or ongoing circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MOTE
    -0.17
    اÙĩ
    -0.16
    .tpl
    -0.16
    ain
    -0.15
     createAction
    -0.15
     ÙĪز
    -0.15
    Ỽp
    -0.15
    stad
    -0.14
     not
    -0.14
    TURE
    -0.14
    POSITIVE LOGITS
     anymore
    0.18
     necessarily
    0.15
    VIDIA
    0.14
    imi
    0.14
    овеÑĢ
    0.14
    λÎŃ
    0.13
    leans
    0.13
    amework
    0.13
    UMAN
    0.13
     enim
    0.13
    Act Density 0.006%

    No Known Activations