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

    Neuronpedia

    INDEX
    Explanations

    phrases related to collaboration and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensen
    -0.17
    åijĺ
    -0.15
    dle
    -0.15
    elong
    -0.15
    STRUCT
    -0.15
    ãĤ¥
    -0.15
    ipple
    -0.14
    çł
    -0.14
     Careers
    -0.14
    ouv
    -0.14
    POSITIVE LOGITS
     forces
    0.46
     Forces
    0.35
    forces
    0.32
     force
    0.24
     Force
    0.19
     efforts
    0.19
     together
    0.18
     closely
    0.18
    åĬĽéĩı
    0.17
     FORCE
    0.16
    Act Density 0.029%

    No Known Activations