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

    Neuronpedia

    INDEX
    Explanations

    references to women and commands in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sc
    -0.33
     sl
    -0.32
     sa
    -0.31
     se
    -0.31
     st
    -0.29
     sk
    -0.29
     sw
    -0.28
     sp
    -0.28
     sm
    -0.28
     sh
    -0.28
    POSITIVE LOGITS
    S
    0.24
    ¡
    0.23
    SB
    0.22
    SX
    0.21
    SZ
    0.21
    SJ
    0.21
    ½
    0.21
    SV
    0.20
    SG
    0.20
    SID
    0.20
    Act Density 0.154%

    No Known Activations