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

    Neuronpedia

    INDEX
    Explanations

    references to "instances" and related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Technologien
    -0.46
    ENDIAN
    -0.44
     preceded
    -0.44
     centenary
    -0.43
     undergraduates
    -0.42
     mechanisms
    -0.42
     culminated
    -0.41
    ENCIAS
    -0.41
     emerging
    -0.40
     traditionally
    -0.40
    POSITIVE LOGITS
     accept
    0.74
     instances
    0.58
     instance
    0.58
    UserScript
    0.58
     Instances
    0.57
     accepts
    0.55
     Accept
    0.54
     claim
    0.54
     للمعارف
    0.54
     INSTANCE
    0.54
    Act Density 0.379%

    No Known Activations