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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate necessity or a requirement to take action

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

    just have to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ainfi
    -0.43
     institutes
    -0.40
     abstrait
    -0.39
    épendant
    -0.39
     processos
    -0.38
     institute
    -0.37
     propósitos
    -0.37
     plufieurs
    -0.36
     vainqueur
    -0.35
     communautaire
    -0.35
    POSITIVE LOGITS
    LookAnd
    0.64
    只要
    0.58
     wystarczy
    0.56
    mogat
    0.56
    Basta
    0.54
    styleType
    0.54
    /**
    0.51
    ۜ
    0.50
     basta
    0.50
     autorytatywna
    0.49
    Act Density 0.031%

    No Known Activations