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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns or possessive determiners followed by a verb indicating actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and their associated verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    renheit
    -0.71
    click
    -0.71
    Exit
    -0.71
    soever
    -0.66
    john
    -0.66
    minster
    -0.64
    ular
    -0.63
    grass
    -0.62
    ackets
    -0.62
    Tonight
    -0.60
    POSITIVE LOGITS
     ensured
    0.81
     disclaim
    0.80
    ItemTracker
    0.76
    ãĥīãĥ©
    0.75
     incentiv
    0.74
     testified
    0.73
     embold
    0.71
     alienated
    0.70
     noted
    0.69
     guiActiveUn
    0.68
    Act Density 0.319%

    No Known Activations