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

    Neuronpedia

    INDEX
    Explanations

    symbols or special characters in conjunction with technical terms and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     organised
    -0.22
     favoured
    -0.20
     neighbours
    -0.20
     organisations
    -0.20
     coloured
    -0.19
    Behaviour
    -0.19
     Behaviour
    -0.19
     specialised
    -0.19
     ‘
    -0.18
    organisation
    -0.18
    POSITIVE LOGITS
     determining
    0.17
     determine
    0.16
     primarily
    0.16
     tùy
    0.16
    	S
    0.15
     but
    0.15
     Sof
    0.15
    -S
    0.15
     its
    0.15
    SOLE
    0.15
    Act Density 0.016%

    No Known Activations