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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "alone."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĵ
    -3.13
    Ĥ
    -3.13
    IJ
    -3.08
    ©
    -3.07
    Ĥ¬
    -3.06
    »¿
    -2.96
    ĻĤ
    -2.93
    ĸ
    -2.87
    Īĺ
    -2.79
    §
    -2.73
    POSITIVE LOGITS
    requency
    1.67
    plic
    1.66
    antry
    1.64
    elve
    1.60
    olta
    1.58
    flix
    1.56
    evol
    1.51
    osto
    1.51
    Tube
    1.47
    igan
    1.45
    Act Density 0.123%

    No Known Activations