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

    Neuronpedia

    INDEX
    Explanations

    instances of specific organizations or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tip
    -0.18
    569
    -0.16
     Jac
    -0.15
     hack
    -0.15
     drag
    -0.14
    ese
    -0.14
     Gaut
    -0.14
    434
    -0.14
     kick
    -0.14
     n
    -0.14
    POSITIVE LOGITS
    elman
    0.15
    hamster
    0.15
    spath
    0.14
    ģm
    0.14
    ENTRY
    0.14
    -Cs
    0.14
    ounder
    0.14
    imates
    0.14
    lland
    0.14
    ymax
    0.14
    Act Density 0.035%

    No Known Activations