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

    Neuronpedia

    INDEX
    Explanations

    descriptive attributes and features of objects or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vrier
    -0.16
    urar
    -0.15
    usz
    -0.15
    禮
    -0.15
    è»
    -0.15
    ovice
    -0.15
    åĹ
    -0.15
    enance
    -0.15
    Hover
    -0.14
    308
    -0.14
    POSITIVE LOGITS
     built
    0.25
     handles
    0.24
     embedded
    0.22
     holes
    0.22
     builtin
    0.21
    Built
    0.21
     Built
    0.21
     compartments
    0.21
     emb
    0.21
    built
    0.20
    Act Density 0.263%

    No Known Activations