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

    Neuronpedia

    INDEX
    Explanations

    phrases with the first-person pronoun "I."

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

    Sentences starting with "I" expressing feelings/thoughts

    np_acts-logits-general · gemini-2.0-flash

    personal actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     my
    -0.58
     myself
    -0.57
    Myself
    -0.53
     Myself
    -0.50
    在我的
    -0.49
    addAll
    -0.49
    Rgds
    -0.48
    sequently
    -0.45
     primarily
    -0.45
    ++]=
    -0.45
    POSITIVE LOGITS
     forgot
    0.84
     swear
    0.79
     hate
    0.76
    GOTREF
    0.71
     mean
    0.70
     love
    0.69
     bet
    0.68
     knew
    0.67
     missed
    0.67
     يتيمه
    0.67
    Act Density 0.237%

    No Known Activations