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

    Neuronpedia

    INDEX
    Explanations

    structural elements and features within architectural or physical descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rale
    -0.18
    MOTE
    -0.15
    rane
    -0.15
    COND
    -0.15
    LOCKS
    -0.15
    ATYPE
    -0.14
    inha
    -0.14
    ocs
    -0.14
    Äįer
    -0.14
    TAIL
    -0.14
    POSITIVE LOGITS
     deck
    0.33
     acc
    0.28
     fest
    0.28
     adorned
    0.27
     embell
    0.27
     covered
    0.27
     enc
    0.27
     bed
    0.25
     clad
    0.25
     outf
    0.25
    Act Density 0.152%

    No Known Activations