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

    Neuronpedia

    INDEX
    Explanations

    references to walls or barriers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oq
    -0.16
    trap
    -0.15
    .clientHeight
    -0.15
     traps
    -0.14
    ÑĢÑĮ
    -0.14
    ÙħاÙĦ
    -0.14
    linger
    -0.14
     Gas
    -0.14
     Emotional
    -0.14
    agan
    -0.14
    POSITIVE LOGITS
    TECTED
    0.17
    ployment
    0.16
    orsch
    0.15
    rastructure
    0.14
    opi
    0.14
    privileged
    0.14
    STALL
    0.14
    íį¼
    0.14
    ör
    0.14
    uja
    0.14
    Act Density 0.003%

    No Known Activations