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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusivity and affirmation in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    슷
    -0.41
     pourtant
    -0.37
     hang
    -0.34
     retail
    -0.33
    一愣
    -0.33
     Belf
    -0.33
     ocz
    -0.32
     Contactez
    -0.30
     hit
    -0.30
     spring
    -0.30
    POSITIVE LOGITS
    IContainer
    0.72
    ########.
    0.61
     SwitchCompat
    0.54
     gyhoeddwyd
    0.54
     hochzeit
    0.53
    pushFollow
    0.50
     Aler
    0.48
     MainAxisSize
    0.48
    دانشنامهٔ
    0.48
     absolutely
    0.48
    Act Density 1.316%

    No Known Activations