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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marin
    -0.48
    otechnology
    -0.47
     Lud
    -0.45
     lud
    -0.44
    portlet
    -0.44
     inst
    -0.44
     Thors
    -0.42
    Eld
    -0.42
    Marin
    -0.41
    terraform
    -0.41
    POSITIVE LOGITS
     agree
    1.59
     Agree
    1.48
    agree
    1.43
     agreement
    1.41
     agreeing
    1.38
     agrees
    1.37
    Agree
    1.36
     agreed
    1.35
     Agreement
    1.31
     Agreed
    1.30
    Act Density 0.185%

    No Known Activations