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

    Neuronpedia

    INDEX
    Explanations

    words related to emotional responses or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @include
    -0.15
    	namespace
    -0.14
    ogany
    -0.13
    atel
    -0.13
    braco
    -0.13
     onDataChange
    -0.13
    .EventArgs
    -0.13
    htub
    -0.12
     Omni
    -0.12
    atters
    -0.12
    POSITIVE LOGITS
    ore
    0.67
    ores
    0.58
    ora
    0.55
    ored
    0.55
    oring
    0.54
    ori
    0.54
    ors
    0.54
    à¥ĭर
    0.53
    oren
    0.53
    ory
    0.53
    Act Density 0.194%

    No Known Activations