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

    Neuronpedia

    INDEX
    Explanations

    references to collective human experiences and emotions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     nakalista
    -0.73
     referenties
    -0.70
    AnchorStyles
    -0.62
    SequentialGroup
    -0.59
    bitat
    -0.58
     Presidencia
    -0.57
     présent
    -0.56
     cof
    -0.54
     Erziehung
    -0.53
     datter
    -0.53
    POSITIVE LOGITS
     themselves
    0.73
     Savo
    0.66
     snippetHide
    0.60
     individual
    0.59
     their
    0.57
     محفوظة
    0.57
    都有
    0.56
    sizeCache
    0.55
    cleros
    0.55
     auroit
    0.53
    Act Density 0.022%

    No Known Activations