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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political pathways and strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ividual
    -0.75
    teness
    -0.71
     coh
    -0.70
    ombies
    -0.67
     contrace
    -0.66
    glomer
    -0.66
     Sting
    -0.66
    mble
    -0.66
     obser
    -0.64
    arus
    -0.62
    POSITIVE LOGITS
    finding
    0.98
     paths
    0.95
     toward
    0.93
    breaking
    0.92
     towards
    0.90
     forward
    0.89
     path
    0.89
    ologies
    0.87
    finder
    0.86
    path
    0.86
    Act Density 0.028%

    No Known Activations