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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity or interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TRIBUN
    -0.52
    marvin
    -0.52
    ########.
    -0.47
     Eastman
    -0.42
    /**
    -0.41
    verwijspagina
    -0.40
     Flynn
    -0.40
     Adamson
    -0.39
    NullException
    -0.38
     inoxydable
    -0.38
    POSITIVE LOGITS
    curious
    0.72
     Charge
    0.69
     curious
    0.68
    Charge
    0.68
     Curious
    0.66
    Curi
    0.66
     CHARGE
    0.66
    Curious
    0.65
    charge
    0.63
     curieux
    0.63
    Act Density 0.117%

    No Known Activations