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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    frequent use of personal pronouns and subjective expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .</
    -0.71
    ãĢĤ
    -0.67
    .}
    -0.66
    .(
    -0.61
     �
    -0.60
    ////
    -0.60
    ãĢij
    -0.60
    .<
    -0.58
    âĢ¢âĢ¢
    -0.58
     -->
    -0.58
    POSITIVE LOGITS
    zbollah
    1.01
    odore
    0.90
    ffield
    0.89
    xiety
    0.87
    vana
    0.85
     certainly
    0.85
    usterity
    0.84
     definitely
    0.82
    %"
    0.82
    pherd
    0.82
    Act Density 0.254%

    No Known Activations