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

    Neuronpedia

    INDEX
    Explanations

    concepts related to influence and guidance

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

    Verbs followed by pronouns

    np_acts-logits-general · gemini-2.0-flash

    showing or causing outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Yourself
    -0.82
     thyself
    -0.81
     yourself
    -0.77
    yourself
    -0.76
    expandindo
    -0.76
     himſelf
    -0.75
     Myself
    -0.75
     myſelf
    -0.73
     ourselves
    -0.72
     yourselves
    -0.72
    POSITIVE LOGITS
     us
    0.67
     both
    0.67
     nicely
    0.61
     him
    0.61
     itself
    0.60
     the
    0.59
     me
    0.57
     many
    0.56
     CreateTagHelper
    0.56
     our
    0.54
    Act Density 0.717%

    No Known Activations