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

    Neuronpedia

    INDEX
    Explanations

    contrastive phrases emphasizing subtleties and nuances

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

    Follows "but" or contains uncommon punctuation/symbols

    np_acts-logits-general · gemini-2.0-flash

    contrasting qualification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    partly
    -0.51
     Fink
    -0.47
     partly
    -0.46
    Unmarshaller
    -0.46
    Selection
    -0.46
    Partly
    -0.44
     partially
    -0.43
    ennheiser
    -0.43
    BLEND
    -0.43
     Partly
    -0.42
    POSITIVE LOGITS
    rungsseite
    0.84
     跳转至
    0.79
    theless
    0.76
    卻
    0.69
     powerful
    0.66
     suffices
    0.65
     pourtant
    0.65
    Powerful
    0.63
    Huge
    0.63
    0.62
    Act Density 0.273%

    No Known Activations