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

    Neuronpedia

    INDEX
    Explanations

    common transitional phrases or conjunctions that indicate connections or sequences in text

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

    following conjunctions or prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.84
     Administrativna
    -0.83
    [@BOS@]
    -0.81
    <unused28>
    -0.81
    <unused8>
    -0.81
    <pad>
    -0.81
    <unused14>
    -0.81
    <unused41>
    -0.81
    <unused74>
    -0.81
    <unused3>
    -0.81
    POSITIVE LOGITS
    There
    0.25
     ningún
    0.24
     mucho
    0.24
     nahilalakip
    0.23
    Much
    0.23
     algún
    0.23
    These
    0.23
     instituição
    0.22
    just
    0.22
     prochains
    0.22
    Act Density 0.151%

    No Known Activations