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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement and disagreement in opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    agreement or concurrence

    np_acts-logits-general · gemini-2.0-flash

    agreement and disagreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bun
    -0.60
     Mal
    -0.59
    kan
    -0.56
     []:
    -0.55
    sej
    -0.55
    Mal
    -0.54
    dal
    -0.54
    mal
    -0.53
    srcs
    -0.53
     Kan
    -0.52
    POSITIVE LOGITS
     Disagree
    1.29
     Agree
    1.20
     Agre
    1.16
    Agre
    1.13
     agrees
    1.13
     AGRE
    1.08
     disagree
    1.08
     Agreements
    1.05
    agree
    1.02
     disagrees
    1.01
    Act Density 0.100%

    No Known Activations