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

    Neuronpedia

    INDEX
    Explanations

    character sequences or patterns resembling visual or textual characters in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BIBSYS
    -0.77
    الدراسه
    -0.69
     RouterModule
    -0.65
    signable
    -0.65
    subsection
    -0.64
     CommonModule
    -0.64
     NgModule
    -0.63
    LoS
    -0.62
    KATH
    -0.62
     województwie
    -0.61
    POSITIVE LOGITS
    [toxicity=0]
    0.69
    0.54
     　
    0.53
       
    0.52
     gynhyrchwyd
    0.51
    SequentialGroup
    0.51
    ...:
    0.51
     المعيارى
    0.50
    scriptcase
    0.50
    　
    0.50
    Act Density 0.673%
    No Known Activations