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

    Neuronpedia

    INDEX
    Explanations

    terms related to construction, modification, or restriction actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISTIC
    -0.20
    IZED
    -0.18
    nty
    -0.18
    thin
    -0.18
    baugh
    -0.18
    ITY
    -0.17
    ATIC
    -0.17
    neau
    -0.16
    lsen
    -0.16
    bery
    -0.16
    POSITIVE LOGITS
    ive
    0.79
    ively
    0.70
    ives
    0.64
    ors
    0.63
    ible
    0.63
    ivity
    0.61
    iveness
    0.57
    eur
    0.51
    iv
    0.49
    ions
    0.49
    Act Density 0.172%

    No Known Activations