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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs indicating personal involvement or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    reflexive pronouns and related constructs within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rium
    -0.75
     Connection
    -0.66
    alez
    -0.65
    aic
    -0.65
    izes
    -0.65
    omy
    -0.64
     Hab
    -0.63
    ific
    -0.63
    idy
    -0.62
    lies
    -0.62
    POSITIVE LOGITS
     embroiled
    1.02
     wondering
    1.01
     needing
    0.96
     inund
    0.88
     besieged
    0.87
     footing
    0.86
     squarely
    0.85
     ens
    0.82
     wanting
    0.82
     stranded
    0.80
    Act Density 0.036%

    No Known Activations