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

    Neuronpedia

    INDEX
    Explanations

    expressions related to the impact of actions on audiences or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucken
    -0.16
    oney
    -0.14
     konkrét
    -0.14
    #__
    -0.14
    shal
    -0.14
    oller
    -0.14
    .gstatic
    -0.14
    tractive
    -0.14
    -BEGIN
    -0.13
    ī
    -0.13
    POSITIVE LOGITS
     entire
    0.19
     heck
    0.16
    eza
    0.15
    swire
    0.15
     opportunity
    0.15
     POSSIBILITY
    0.14
     Muse
    0.14
    ä¸Ģä¸ĭ
    0.14
     Gas
    0.13
    offsetof
    0.13
    Act Density 0.469%

    No Known Activations