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

    Neuronpedia

    INDEX
    Explanations

    assertions of agreement or consensus among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gamb
    -0.35
    trät
    -0.33
     bati
    -0.32
     defaultstate
    -0.32
     rumours
    -0.31
     fers
    -0.31
     Gab
    -0.31
     rumors
    -0.31
     Cas
    -0.31
     Fad
    -0.29
    POSITIVE LOGITS
     agree
    3.33
     agrees
    3.02
     agreement
    2.98
     Agree
    2.94
     agreeing
    2.86
     agreed
    2.86
    agree
    2.81
    Agree
    2.78
    agreed
    2.59
     Agreed
    2.58
    Act Density 0.762%

    No Known Activations