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

    Neuronpedia

    INDEX
    Explanations

    phrases that express providing information or insights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Instruction
    -0.17
    iras
    -0.15
    iven
    -0.15
    unami
    -0.15
    entai
    -0.15
    ÎIJ
    -0.14
    aska
    -0.14
    uentes
    -0.14
    ahoma
    -0.14
    phinx
    -0.14
    POSITIVE LOGITS
     idea
    0.60
     Idea
    0.48
    idea
    0.46
     sense
    0.39
     notion
    0.35
     indication
    0.35
     feel
    0.33
     IDEA
    0.30
     handle
    0.30
    sense
    0.29
    Act Density 0.137%

    No Known Activations