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

    Neuronpedia

    INDEX
    Explanations

    expressions of thought, opinion, or consideration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     väli
    -0.70
    orithmic
    -0.59
     Audiodateien
    -0.57
    setViewportView
    -0.54
     Fieber
    -0.54
    DockStyle
    -0.52
    蜓
    -0.51
    Selen
    -0.51
     čet
    -0.51
     comprimidos
    -0.50
    POSITIVE LOGITS
     think
    1.34
     thinks
    1.30
     believe
    1.26
     believes
    1.22
     THINK
    1.17
    think
    1.16
     believed
    1.14
    believe
    1.13
     thought
    1.11
     believing
    1.08
    Act Density 0.267%

    No Known Activations