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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activities and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    references to different parties involved in incidents or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anism
    -0.70
    Lenin
    -0.68
     IPM
    -0.65
    iste
    -0.64
     Own
    -0.63
    ople
    -0.61
    Default
    -0.60
    ISTORY
    -0.58
     Erdogan
    -0.58
    $.
    -0.58
    POSITIVE LOGITS
    ngth
    0.96
     undisclosed
    0.79
    intendent
    0.77
     unnamed
    0.76
    worldly
    0.71
     bombshell
    0.69
    iece
    0.68
    ividual
    0.68
     unidentified
    0.68
     batch
    0.68
    Act Density 0.137%

    No Known Activations