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

    Neuronpedia

    INDEX
    Explanations

    locations and references to situational awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     here
    -0.15
    ibox
    -0.14
    anka
    -0.14
    anca
    -0.14
    aro
    -0.14
     nowhere
    -0.14
     anywhere
    -0.14
     everywhere
    -0.14
     somehow
    -0.14
     Bor
    -0.13
    POSITIVE LOGITS
     located
    0.18
    -hide
    0.17
    located
    0.17
     location
    0.17
    SSIP
    0.16
    ardon
    0.15
     concentration
    0.15
    تÙħر
    0.15
    arkin
    0.14
    ehr
    0.14
    Act Density 0.146%

    No Known Activations