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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ease and convenience in actions or processes

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

    easiest to prefer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.70
     utafitiHapana
    -0.59
    >--}}
    -0.57
    ArrowToggle
    -0.57
    /*
    -0.55
     AssemblyCulture
    -0.54
     الرياضيه
    -0.54
    /**
    -0.54
    lgari
    -0.52
    ➯
    -0.52
    POSITIVE LOGITS
    preferred
    0.64
     prefer
    0.59
     preferred
    0.58
    prefer
    0.57
    best
    0.56
     prefier
    0.52
     best
    0.52
    better
    0.51
     liever
    0.49
     prefers
    0.49
    Act Density 0.351%

    No Known Activations