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

    Neuronpedia

    INDEX
    Explanations

    phrases related to problem-solving or figuring things out

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.91
     nahilalakip
    -0.86
    Diwedd
    -0.84
    ExtendWith
    -0.84
    BeginContext
    -0.82
    EndInit
    -0.81
    Geplaatst
    -0.79
    -0.79
     '\\;'
    -0.77
     BIBSYS
    -0.75
    POSITIVE LOGITS
     solved
    0.70
    gup
    0.66
     problems
    0.66
     riddle
    0.65
     Plank
    0.65
     PROBLEMS
    0.64
     solve
    0.64
     solves
    0.64
     solutions
    0.63
    findung
    0.63
    Act Density 0.007%

    No Known Activations