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

    Neuronpedia

    INDEX
    Explanations

    terms related to decision-making processes and analytical techniques

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

    decision making and choice probabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #+#
    -0.50
    jspb
    -0.49
    tvguidetime
    -0.48
     utafitiHapana
    -0.46
    AccessorTable
    -0.46
    tanleria
    -0.43
    DebuggerNonUser
    -0.42
    UnusedPrivate
    -0.41
    Rujuakan
    -0.41
    WriteLiteral
    -0.40
    POSITIVE LOGITS
     judgments
    0.57
    ungsanleitung
    0.56
     Judgment
    0.52
     judgment
    0.51
     decision
    0.50
     judgements
    0.48
     assessments
    0.47
     procédures
    0.47
     assessment
    0.46
     judgement
    0.45
    Act Density 0.022%

    No Known Activations