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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and questions concerning moral or ethical implications

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

    Word after "if"

    np_acts-logits-general · gemini-2.0-flash

    conditional clauses and sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.53
    '])->
    -0.51
     usually
    -0.49
    Spire
    -0.47
     surprisingly
    -0.45
    beza
    -0.44
     Usually
    -0.44
    Usually
    -0.44
    usually
    -0.43
    ]),
    -0.42
    POSITIVE LOGITS
     prétend
    0.69
     esternos
    0.69
     indeed
    0.65
     fakty
    0.65
     inderdaad
    0.65
     memang
    0.64
     benar
    0.64
    truly
    0.63
    contentLoaded
    0.62
    windowFixed
    0.61
    Act Density 0.199%

    No Known Activations