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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases in sentences

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

    "and" followed by a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    thoughts and feelings after "and"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     themselves
    -0.60
     resulted
    -0.55
    homonymie
    -0.55
     Himself
    -0.55
    themselves
    -0.55
     Itself
    -0.55
     CreateTagHelper
    -0.54
    ">—
    -0.54
     herself
    -0.51
     himself
    -0.51
    POSITIVE LOGITS
     thought
    0.96
     wanted
    0.87
     knew
    0.85
    thought
    0.84
     although
    0.83
     liked
    0.81
     thinks
    0.79
     menyukai
    0.78
     hadn
    0.77
     felt
    0.75
    Act Density 0.265%

    No Known Activations