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

    Neuronpedia

    INDEX
    Explanations

    phrases related to goals and objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esa
    -0.19
    eso
    -0.18
    al
    -0.17
    uous
    -0.16
    don
    -0.16
    /email
    -0.16
    ation
    -0.15
    burger
    -0.15
    eed
    -0.15
    equ
    -0.14
    POSITIVE LOGITS
    getter
    0.22
    posts
    0.22
    /target
    0.20
    setter
    0.20
    keepers
    0.19
    ÙħÙĨد
    0.18
    lessly
    0.18
    post
    0.17
    -setting
    0.17
    /go
    0.17
    Act Density 0.024%

    No Known Activations