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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate collaboration or association

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

    "With" followed by a noun phrase

    np_acts-logits-general · gemini-2.0-flash

    With a / an / the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    toMatchSnapshot
    -0.56
    プライズ
    -0.52
    yyj
    -0.52
    ontale
    -0.52
    TagMode
    -0.50
    <bos>
    -0.50
     resourceCulture
    -0.49
    IsContent
    -0.49
     adipis
    -0.46
    ones
    -0.44
    POSITIVE LOGITS
     plenty
    0.83
     everyone
    0.77
     each
    0.76
    Aholisi
    0.74
     plans
    0.74
    ".
    0.72
     ciascuno
    0.69
     roots
    0.69
     lots
    0.69
     للاسماء
    0.69
    Act Density 0.130%

    No Known Activations