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

    Neuronpedia

    INDEX
    Explanations

    actions and processes related to change, creation, and functioning dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    their
    -0.24
    the
    -0.23
    that
    -0.22
    to
    -0.22
    er
    -0.22
    they
    -0.20
    eh
    -0.20
    than
    -0.20
    test
    -0.19
    this
    -0.19
    POSITIVE LOGITS
     itself
    0.35
    heets
    0.28
    ’
    0.24
    '
    0.24
    cales
    0.23
    cape
    0.21
    cribes
    0.21
     Ñģобой
    0.20
    izes
    0.20
    creens
    0.19
    Act Density 0.742%

    No Known Activations