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

    Neuronpedia

    INDEX
    Explanations

    informal speech patterns and conversational phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Color
    -0.16
    Color
    -0.16
     consenting
    -0.15
    Äĥm
    -0.15
    enting
    -0.14
    ochrome
    -0.14
    icer
    -0.14
    omap
    -0.14
     Fol
    -0.14
    ynchronously
    -0.14
    POSITIVE LOGITS
     Bearing
    0.20
     Latter
    0.19
     NB
    0.18
    NB
    0.17
     Specialist
    0.17
     Equ
    0.15
     Regular
    0.15
     bearing
    0.15
     Cruc
    0.15
     Regents
    0.15
    Act Density 0.534%

    No Known Activations