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

    Neuronpedia

    INDEX
    Explanations

    specific examples or instances of things

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce examples or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neighb
    -0.63
    ULTS
    -0.63
    orts
    -0.63
     unlaw
    -0.57
    ISA
    -0.55
    ggles
    -0.55
     suspic
    -0.54
    ements
    -0.54
    atures
    -0.53
     unification
    -0.53
    POSITIVE LOGITS
    .,
    0.78
    ,
    0.74
    ,.
    0.72
    ,—
    0.69
    ,,
    0.68
    ,...
    0.66
    .
    0.64
    :#
    0.63
    ;
    0.63
    :{
    0.62
    Act Density 0.037%

    No Known Activations