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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal interactions or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating admiration or respect for individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.67
    orts
    -0.64
    amaru
    -0.56
    ocy
    -0.56
    obos
    -0.55
    RESULTS
    -0.53
    igators
    -0.53
    ãĥ©ãĥ³
    -0.53
    yg
    -0.53
    amas
    -0.53
    POSITIVE LOGITS
    someone
    1.32
     somebody
    1.18
     someone
    1.17
     something
    1.09
    something
    1.09
     Someone
    1.08
     Something
    1.03
     preferably
    1.03
     an
    1.01
     a
    1.00
    Act Density 0.427%

    No Known Activations