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

    Neuronpedia

    INDEX
    Explanations

    concepts related to attachment and genetic conditions

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

    disorders, fines, dysfunction, discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.59
    LEncoder
    -0.57
     houſe
    -0.57
    IntoConstraints
    -0.56
     propOrder
    -0.56
    Autoritní
    -0.54
     pleaſure
    -0.53
     Houſe
    -0.52
     purpoſe
    -0.52
    adaptiveStyles
    -0.51
    POSITIVE LOGITS
     loss
    0.35
     wrongs
    0.34
     Paglinawan
    0.33
     wijze
    0.32
    loem
    0.30
     commonwealth
    0.29
     dise
    0.28
     restoration
    0.28
     risolvere
    0.28
     …
    0.28
    Act Density 0.151%

    No Known Activations