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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing opinions or common knowledge

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

    Follows "like", "O", or describes sensitivity

    np_acts-logits-general · gemini-2.0-flash

    like : or like :

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mijne
    -0.60
    esModule
    -0.54
     kasarigan
    -0.53
     colgante
    -0.51
     nemlig
    -0.50
     թվական
    -0.50
     istrinya
    -0.49
     colgantes
    -0.47
     esclavos
    -0.47
    Pratique
    -0.47
    POSITIVE LOGITS
     basic
    0.51
    ...
    0.49
     conce
    0.47
    (;;)
    0.46
     ſind
    0.45
     formal
    0.45
     minor
    0.44
    ..
    0.43
     sp
    0.43
     finger
    0.43
    Act Density 0.113%

    No Known Activations