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

    Neuronpedia

    INDEX
    Explanations

    phrases that express or indicate negotiations, discussions, or exchanges involving multiple parties or elements

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

    Comes after the word "and"

    np_acts-logits-general · gemini-2.0-flash

    connecting actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     می‌
    -0.53
    titleMargin
    -0.51
    bad
    -0.49
    chow
    -0.48
    Legături
    -0.47
    PMailer
    -0.46
    flashdata
    -0.46
     briefs
    -0.43
     tels
    -0.43
    raw
    -0.43
    POSITIVE LOGITS
     be
    1.13
     create
    1.01
     achieve
    1.00
     make
    0.99
     generate
    0.98
     develop
    0.97
     improve
    0.97
     raise
    0.95
     protect
    0.94
     receive
    0.94
    Act Density 0.334%

    No Known Activations