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

    Neuronpedia

    INDEX
    Explanations

    environmental references and critical infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wald
    -0.15
    pector
    -0.15
     cliff
    -0.14
    .IntPtr
    -0.14
    sheet
    -0.14
    å°ģ
    -0.14
     mountain
    -0.14
    éĤ£éĩĮ
    -0.14
    Vars
    -0.13
     sidel
    -0.13
    POSITIVE LOGITS
     Alle
    0.24
     Great
    0.24
    Alle
    0.22
    Miss
    0.22
     Mississippi
    0.21
     Sus
    0.20
     Ou
    0.19
     MISS
    0.19
    Great
    0.19
     Columbia
    0.19
    Act Density 0.167%

    No Known Activations