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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or contemplation related to personal experiences

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

    Followed by a pronoun after comma

    np_acts-logits-general · gemini-2.0-flash

    punctuation followed by pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     */;
    -0.87
    جستارهای
    -0.75
     typelib
    -0.71
    tvguidetime
    -0.71
    -0.70
     նաև
    -0.69
    ſelf
    -0.69
     خارجية
    -0.69
    */;
    -0.69
     '\\;'
    -0.68
    POSITIVE LOGITS
     yeah
    0.97
     it
    0.88
     they
    0.87
     I
    0.84
     yes
    0.80
     there
    0.80
     we
    0.74
    yeah
    0.73
     guess
    0.72
     you
    0.70
    Act Density 0.239%

    No Known Activations