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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating activities and places of interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .fm
    -0.15
    ele
    -0.15
    Å¡k
    -0.14
    agher
    -0.13
    anol
    -0.13
     ç¸
    -0.13
    obar
    -0.13
    vir
    -0.13
    ACLE
    -0.13
    778
    -0.13
    POSITIVE LOGITS
     things
    0.35
     Things
    0.35
     activities
    0.31
    Things
    0.30
     thing
    0.28
     Activities
    0.28
    things
    0.27
    activities
    0.26
    Activities
    0.25
     Thing
    0.24
    Act Density 0.036%

    No Known Activations