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

    Neuronpedia

    INDEX
    Explanations

    phrases about mathematical or scientific concepts involving sets, separations, and distinct objects

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

    "one" followed by "for" or preposition

    np_acts-logits-general · gemini-2.0-flash

    one for each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.63
    PasswordEncoder
    -0.51
     nổi
    -0.49
    ∭
    -0.48
     '{@
    -0.48
    一身
    -0.48
     dis
    -0.47
    duo
    -0.47
    latter
    -0.47
    nicy
    -0.46
    POSITIVE LOGITS
     each
    1.09
     every
    1.07
    every
    1.04
     Chaque
    1.04
     chaque
    1.00
     Each
    0.97
     varje
    0.96
    Chaque
    0.95
    Each
    0.94
    each
    0.93
    Act Density 0.356%

    No Known Activations