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

    Neuronpedia

    INDEX
    Explanations

    references to appendices or supplemental material

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amer
    -0.17
     T
    -0.17
    ÑĢажд
    -0.15
    adele
    -0.15
     Schwarz
    -0.15
     Amer
    -0.15
     Valley
    -0.14
    anco
    -0.14
    eron
    -0.14
    ÅĤaw
    -0.14
    POSITIVE LOGITS
     èģĶ
    0.17
    RC
    0.16
    .scalablytyped
    0.15
    ucken
    0.14
    ota
    0.14
    iol
    0.14
    ovi
    0.14
    -cli
    0.13
     Operand
    0.13
    feld
    0.13
    Act Density 0.036%

    No Known Activations