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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and formatting cues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     realize
    -0.22
    localized
    -0.21
    Color
    -0.21
    Colors
    -0.20
     accompl
    -0.20
     realizes
    -0.20
     Color
    -0.19
     realized
    -0.19
    neighbor
    -0.19
     color
    -0.18
    POSITIVE LOGITS
     whilst
    0.34
     Bearing
    0.28
     bearing
    0.27
    ££
    0.25
    £
    0.25
     Whilst
    0.24
    bearing
    0.24
     NB
    0.23
     £
    0.23
    NB
    0.23
    Act Density 0.854%

    No Known Activations