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

    Neuronpedia

    INDEX
    Explanations

    words related to human involvement in environmental changes or societal issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.95
    alos
    -0.93
    byss
    -0.87
    asso
    -0.85
    skilled
    -0.79
    lust
    -0.78
    earchers
    -0.78
    yip
    -0.78
    achus
    -0.77
    oother
    -0.76
    POSITIVE LOGITS
     disaster
    0.79
     version
    0.77
     disasters
    0.76
     pseudo
    0.76
     goodies
    0.74
     versions
    0.73
     garbage
    0.70
     horrors
    0.69
     interventions
    0.69
     goods
    0.68
    Act Density 0.068%

    No Known Activations