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

    Neuronpedia

    INDEX
    Explanations

    words related to receiving something by someone

    oai_token-act-pair · gpt-3.5-turbo

    terms related to recipients and their interactions in communication contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udic
    -0.75
    hov
    -0.67
     Alban
    -0.62
    anova
    -0.61
    INS
    -0.61
    coll
    -0.59
     ABE
    -0.59
     Alb
    -0.58
    ERO
    -0.57
     slic
    -0.57
    POSITIVE LOGITS
    ients
    0.96
    alled
    0.88
    ience
    0.86
    ipient
    0.86
    algia
    0.85
    soever
    0.81
    alling
    0.76
    IUM
    0.76
    eous
    0.76
    ient
    0.75
    Act Density 0.072%

    No Known Activations