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

    Neuronpedia

    INDEX
    Explanations

    questions regarding the existence and functionality of APIs and methods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Ovid
    -0.54
    uramente
    -0.53
     kwamba
    -0.52
    DebuggerNonUser
    -0.52
     WaitForSeconds
    -0.51
     admittedly
    -0.51
     שנים
    -0.49
    >>>>>>>
    -0.48
     הרבה
    -0.48
    åde
    -0.47
    POSITIVE LOGITS
    ?
    1.18
    ?"
    1.16
    ?
    1.13
    ?)
    1.13
    ؟
    1.13
    ?</
    1.10
    ?”
    1.09
    ?'
    1.09
    ?}
    1.08
    ?).
    1.08
    Act Density 1.931%

    No Known Activations