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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or changes

    oai_token-act-pair · gpt-3.5-turbo

    personal reflections and expressions of feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.66
     respectively
    -0.60
     omin
    -0.59
     apiece
    -0.57
    Their
    -0.56
    anwhile
    -0.54
     occupants
    -0.53
     turnover
    -0.51
     Us
    -0.51
     incumb
    -0.51
    POSITIVE LOGITS
     myself
    1.47
     my
    0.96
     crochet
    0.76
     blogging
    0.67
    oan
    0.65
    poke
    0.64
     personally
    0.62
     writing
    0.62
    aido
    0.61
    watching
    0.60
    Act Density 0.954%

    No Known Activations