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

    Neuronpedia

    INDEX
    Explanations

    expressions related to "hell" or extreme negative situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     joint
    -0.48
     push
    -0.47
     ra
    -0.45
     tid
    -0.45
     Inc
    -0.43
     inc
    -0.42
     pep
    -0.42
     ch
    -0.42
     Ses
    -0.42
     plot
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.71
    RTDA
    0.69
     صوتيه
    0.65
     NgModule
    0.61
     snippetHide
    0.61
     '\\;'
    0.60
     ciudadana
    0.59
    UserScript
    0.59
    Становништво
    0.59
    #
    0.58
    Act Density 0.497%

    No Known Activations