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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating avoidance and the desire for personal space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingles
    -0.20
    rna
    -0.18
     somewhat
    -0.17
     khá
    -0.17
     rather
    -0.17
     bastante
    -0.17
     quite
    -0.16
     both
    -0.16
    574
    -0.15
     almost
    -0.15
    POSITIVE LOGITS
     nor
    0.29
     necessarily
    0.26
     anymore
    0.24
    ecessarily
    0.23
     Nor
    0.21
    Nor
    0.19
    WXYZ
    0.17
    every
    0.17
    nor
    0.17
     every
    0.16
    Act Density 0.374%

    No Known Activations