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

    Neuronpedia

    INDEX
    Explanations

    references to changes and transformations in societal norms or practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oleon
    -0.16
    actable
    -0.15
    erb
    -0.15
    rát
    -0.14
     Redistributions
    -0.14
    oog
    -0.14
    loit
    -0.14
     opak
    -0.14
    rnek
    -0.14
    iasm
    -0.14
    POSITIVE LOGITS
     abandon
    0.52
     ditch
    0.49
     abandoned
    0.46
     abandonment
    0.43
     abandoning
    0.43
     fors
    0.37
     discard
    0.35
     discarded
    0.34
     dropped
    0.34
     Dump
    0.33
    Act Density 0.677%

    No Known Activations