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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to selection or removal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CSP
    -0.49
    CSP
    -0.46
    featureID
    -0.44
    Personensuche
    -0.44
    HasAnnotation
    -0.43
    LikeLike
    -0.43
     xPos
    -0.40
    一方
    -0.40
     despite
    -0.38
    toContain
    -0.38
    POSITIVE LOGITS
     zijne
    0.65
     avoient
    0.64
     zoude
    0.61
     dezelve
    0.60
     gustaMe
    0.59
    genodigd
    0.57
     auroit
    0.57
    guiente
    0.56
     étoient
    0.55
    ghed
    0.55
    Act Density 0.510%

    No Known Activations