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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or the presence of certain groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.98
    AndEndTag
    -0.90
     Roskov
    -0.89
     nakalista
    -0.78
    клопе
    -0.75
     acceptez
    -0.74
     calendriers
    -0.71
     Bioaccumulative
    -0.71
     utafitiHapana
    -0.71
    GEBURTSDATUM
    -0.70
    POSITIVE LOGITS
     Some
    0.84
     some
    0.79
    Some
    0.73
     unele
    0.68
     Many
    0.66
     algunas
    0.64
     некоторые
    0.64
     many
    0.63
     algunos
    0.62
     sommige
    0.60
    Act Density 0.343%

    No Known Activations