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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "mind" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otify
    -0.16
    aurus
    -0.15
    ritz
    -0.15
    antino
    -0.15
    akedown
    -0.15
    EZ
    -0.14
    ureka
    -0.14
     strides
    -0.14
    aylor
    -0.14
    eyer
    -0.14
    POSITIVE LOGITS
    fulness
    0.29
    lessly
    0.26
    sets
    0.25
    ustry
    0.24
    -num
    0.23
    fully
    0.23
    /body
    0.23
    fuck
    0.23
    -body
    0.22
     blowing
    0.22
    Act Density 0.008%

    No Known Activations