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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "From."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukkit
    -0.18
     Wake
    -0.15
    332
    -0.15
     Naked
    -0.14
    regor
    -0.14
    ÙĦ
    -0.14
    ersist
    -0.14
    Wake
    -0.14
     Rat
    -0.14
    iable
    -0.14
    POSITIVE LOGITS
    odes
    0.15
    opot
    0.15
    ÑĤаб
    0.15
    idal
    0.15
    rán
    0.15
    ardown
    0.14
    ØŃØ©
    0.14
    pections
    0.14
    onds
    0.14
    oldown
    0.14
    Act Density 0.036%

    No Known Activations