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

    Neuronpedia

    INDEX
    Explanations

    sentences discussing beliefs or opinions

    oai_token-act-pair · gpt-3.5-turbo

    statements of belief or assessment regarding states and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Includes
    -0.81
     Cosponsors
    -0.72
    quished
    -0.68
    obbies
    -0.68
    gian
    -0.67
     recounts
    -0.65
     mentions
    -0.65
     Adds
    -0.64
     remem
    -0.62
    }{
    -0.62
    POSITIVE LOGITS
     doomed
    1.20
     destined
    1.17
     poised
    1.12
     ripe
    1.11
     achievable
    1.10
     progressing
    1.10
     slipping
    1.08
     headed
    1.07
     ready
    1.06
     nearing
    1.05
    Act Density 0.307%

    No Known Activations