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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or dramatic actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal issues and political situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    their
    -0.81
    they
    -0.76
     *.
    -0.67
     THEY
    -0.67
     theirs
    -0.65
    They
    -0.64
    $.
    -0.63
     THEIR
    -0.63
    )).
    -0.63
     They
    -0.62
    POSITIVE LOGITS
     himself
    1.13
     his
    0.85
     athlet
    0.83
     herself
    0.82
     onstage
    0.76
     backstage
    0.75
    iership
    0.75
    His
    0.75
     coaching
    0.74
     solo
    0.73
    Act Density 0.684%

    No Known Activations