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

    Neuronpedia

    INDEX
    Explanations

    references to objectives or goals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lak
    -0.17
    dw
    -0.17
    eso
    -0.16
    esa
    -0.16
    esz
    -0.15
    ei
    -0.15
    ermen
    -0.15
    burgh
    -0.15
    don
    -0.14
    dar
    -0.14
    POSITIVE LOGITS
    /target
    0.20
    lessly
    0.19
    /go
    0.18
    inalg
    0.17
    swith
    0.15
    ingerprint
    0.15
     goals
    0.15
    ulfilled
    0.15
    charset
    0.14
    ÅĻich
    0.14
    Act Density 0.035%

    No Known Activations