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

    Neuronpedia

    INDEX
    Explanations

    terms related to mechanics and economics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thought
    -0.17
    hou
    -0.17
    ings
    -0.16
    ishment
    -0.16
    hide
    -0.15
    unge
    -0.15
    üyük
    -0.15
    eb
    -0.15
    hol
    -0.14
    tings
    -0.14
    POSITIVE LOGITS
    ALLY
    0.30
    ally
    0.24
    ymbols
    0.16
    entric
    0.16
    entr
    0.15
    ymb
    0.15
    rece
    0.14
    -minded
    0.14
    ians
    0.14
    ailer
    0.14
    Act Density 0.069%

    No Known Activations