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

    Neuronpedia

    INDEX
    Explanations

    instances of temporal phrases indicating time or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingt
    -0.22
     немÑĥ
    -0.17
    ÑģÑİ
    -0.15
    Fullscreen
    -0.15
    ãģĬãĤĬ
    -0.15
    shot
    -0.14
    role
    -0.14
    ossible
    -0.14
    icking
    -0.14
    latin
    -0.14
    POSITIVE LOGITS
     inception
    0.26
     then
    0.23
     none
    0.23
     childhood
    0.23
     nobody
    0.21
     nothing
    0.21
     they
    0.20
    forth
    0.20
     we
    0.20
     there
    0.20
    Act Density 0.045%

    No Known Activations