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

    Neuronpedia

    INDEX
    Explanations

    various aspects of personal and professional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erule
    -0.16
    Äįit
    -0.15
    riere
    -0.15
    arked
    -0.15
    fsp
    -0.15
    -valu
    -0.14
    chimp
    -0.13
    ãĥ¼ãĥ
    -0.13
    feit
    -0.13
    ç¹Ķ
    -0.13
    POSITIVE LOGITS
     secure
    0.39
     secured
    0.39
     securing
    0.35
     convince
    0.32
    secure
    0.32
    secured
    0.32
     sec
    0.32
     persuade
    0.31
    sec
    0.30
     Secure
    0.29
    Act Density 0.547%

    No Known Activations