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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like."

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

    just like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     réseaux
    -0.46
     Belum
    -0.45
     Budaya
    -0.45
     extranjera
    -0.44
     seriously
    -0.44
     zahrani
    -0.44
     køb
    -0.43
     paleta
    -0.43
     paulista
    -0.42
     mulighed
    -0.42
    POSITIVE LOGITS
    __*/
    0.73
    unlike
    0.56
     uLocal
    0.56
    __(/*!
    0.56
    importe
    0.55
    Tikang
    0.54
    (!__
    0.51
    identical
    0.50
    Exactly
    0.50
    KommentareTeilen
    0.50
    Act Density 0.005%

    No Known Activations