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

    Neuronpedia

    INDEX
    Explanations

    references to safety and structural stability issues in mining contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ELLOW
    -0.16
     verv
    -0.15
    onom
    -0.15
    ål
    -0.15
    orgh
    -0.14
     Trojan
    -0.14
    aptic
    -0.14
    ->↵
    -0.14
     Pip
    -0.14
    Ī
    -0.14
    POSITIVE LOGITS
     headings
    0.23
     drift
    0.23
     tunnel
    0.22
     Tunnel
    0.20
     bench
    0.20
     galleries
    0.19
     heading
    0.19
     portal
    0.19
     face
    0.19
     portals
    0.18
    Act Density 0.020%

    No Known Activations