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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their usage in relation to actions and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ability
    -0.27
     able
    -0.26
    able
    -0.24
     possibilities
    -0.22
     possibility
    -0.21
     Able
    -0.21
    åı¯
    -0.20
    izable
    -0.20
    Ability
    -0.20
     возможноÑģÑĤи
    -0.20
    POSITIVE LOGITS
    ingham
    0.17
    еÑĤÑĮ
    0.16
    athy
    0.16
     cand
    0.15
     Setter
    0.15
    pire
    0.14
    виÑĩ
    0.14
    elyn
    0.14
     ca
    0.14
    lesh
    0.14
    Act Density 0.108%

    No Known Activations