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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements related to construction projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onRequest
    -0.17
    ALAR
    -0.16
     scaff
    -0.15
    ocking
    -0.14
    lam
    -0.14
    جار
    -0.14
     Lad
    -0.14
     streams
    -0.14
     sustained
    -0.14
    annie
    -0.14
    POSITIVE LOGITS
     tunnel
    0.27
     tun
    0.26
     Tunnel
    0.26
     tunnels
    0.26
     Segment
    0.23
     alignments
    0.22
     Constructors
    0.22
     bored
    0.21
     segment
    0.21
     Alignment
    0.20
    Act Density 0.086%

    No Known Activations