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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating uncertainty or hesitation regarding future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerPixel
    -0.16
    ä¸įå¾Ĺ
    -0.16
    lius
    -0.14
    erie
    -0.14
    íĥĪ
    -0.14
    estring
    -0.14
    ÑĢиÑĩ
    -0.14
    ensa
    -0.14
    upy
    -0.14
    .delay
    -0.14
    POSITIVE LOGITS
     anytime
    0.36
     soon
    0.34
     unless
    0.32
    soon
    0.31
    unless
    0.26
     Soon
    0.26
     until
    0.24
     likely
    0.24
     near
    0.23
     Unless
    0.23
    Act Density 0.108%

    No Known Activations