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

    Neuronpedia

    INDEX
    Explanations

    specific names associated with prominent public figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    letico
    -0.70
     pregn
    -0.69
    erala
    -0.68
     Pixie
    -0.68
    loads
    -0.66
    alach
    -0.64
    population
    -0.64
    ATHER
    -0.63
    plays
    -0.63
     dolphin
    -0.63
    POSITIVE LOGITS
    feld
    1.09
    hetti
    0.93
    heimer
    0.91
    owitz
    0.88
    stein
    0.86
    bard
    0.86
    bach
    0.84
    baum
    0.84
    wald
    0.84
    berg
    0.83
    Act Density 0.003%

    No Known Activations