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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate collective actions or combined effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     universel
    -0.38
    _();
    -0.37
     bulunan
    -0.36
     rychle
    -0.36
     LINKS
    -0.36
     polémica
    -0.36
     particules
    -0.35
     inmediato
    -0.35
     apparaître
    -0.34
    prechpartner
    -0.34
    POSITIVE LOGITS
    Together
    0.85
     combined
    0.82
     collectively
    0.81
    together
    0.80
    combined
    0.77
     Together
    0.77
    Combined
    0.75
     together
    0.75
     collective
    0.73
     Combined
    0.73
    Act Density 0.714%

    No Known Activations