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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or transfer

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating direction or movement towards something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entimes
    -0.74
    gang
    -0.73
    cu
    -0.72
    geist
    -0.72
    uren
    -0.69
    zai
    -0.68
    yip
    -0.67
    anguage
    -0.65
    cies
    -0.64
    ILA
    -0.63
    POSITIVE LOGITS
     adulthood
    1.18
     ob
    0.83
     existence
    0.83
     orbit
    0.82
     unch
    0.79
     classrooms
    0.77
    jected
    0.74
     infinity
    0.73
     adolescence
    0.72
     hypers
    0.70
    Act Density 0.108%

    No Known Activations