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

    Neuronpedia

    INDEX
    Explanations

    verbs related to change or development

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the functioning and evolution of systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teness
    -0.70
     Clarks
    -0.67
    osate
    -0.66
    isky
    -0.64
     Rouge
    -0.64
    OTOS
    -0.62
     Frazier
    -0.61
     Albion
    -0.60
     Tanz
    -0.60
    âĻ¦
    -0.60
    POSITIVE LOGITS
     handled
    0.84
     structured
    0.82
     fared
    0.82
     unfolded
    0.79
     shaping
    0.79
     manifest
    0.78
    ribed
    0.77
     interact
    0.76
     behave
    0.76
     relate
    0.73
    Act Density 0.157%

    No Known Activations